Search

The utility of large language models (LLMs) depends heavily on the quality and quantity of their training data. Many organizations possess large data corpora that could be leveraged to train or fine-tune LLMs tailored to their specific needs. However, these datasets often come with access restrictions that are based on user privileges and enforced by access control mechanisms. Training LLMs on such datasets could result in exposure of sensitive information to unauthorized users. A straightforward approach for preventing such exposure is to train a separate model for each access level. This, however, may result in low utility models due to the limited amount of training data per model compared to the amount in the entire organizational corpus. Another approach is to train a single LLM on all the data while limiting the exposure of unauthorized information. However, current exposure-limiting methods for LLMs are ineffective for access-controlled data, where sensitive information appears frequently across many training examples. We propose DOMBA - double model balancing - a simple approach for training and deploying LLMs that provides high utility and access-control functionality with security guarantees. DOMBA aggregates the probability distributions of two models, each trained on documents with (potentially many) different access levels, using a "min-bounded" average function (a function that is bounded by the smaller value, e.g., harmonic mean). A detailed mathematical analysis and extensive evaluation show that DOMBA safeguards restricted information while offering utility comparable to non-secure models., Comment: 11 pages, 3 figures

Serverless computing is an emerging cloud paradigm with serverless functions at its core. While serverless environments enable software developers to focus on developing applications without the need to actively manage the underlying runtime infrastructure, they open the door to a wide variety of security threats that can be challenging to mitigate with existing methods. Existing security solutions do not apply to all serverless architectures, since they require significant modifications to the serverless infrastructure or rely on third-party services for the collection of more detailed data. In this paper, we present an extendable serverless security threat detection model that leverages cloud providers' native monitoring tools to detect anomalous behavior in serverless applications. Our model aims to detect compromised serverless functions by identifying post-exploitation abnormal behavior related to different types of attacks on serverless functions, and therefore, it is a last line of defense. Our approach is not tied to any specific serverless application, is agnostic to the type of threats, and is adaptable through model adjustments. To evaluate our model's performance, we developed a serverless cybersecurity testbed in an AWS cloud environment, which includes two different serverless applications and simulates a variety of attack scenarios that cover the main security threats faced by serverless functions. Our evaluation demonstrates our model's ability to detect all implemented attacks while maintaining a negligible false alarm rate.

Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely explanation for the person's discomfort, thereby alleviating the need for further information. This example illustrates how subtle visual cues can challenge our cognitive skills and demonstrates the complexity of interpreting visual scenarios. To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge. The benchmark comprises 400 visual riddles, each featuring a unique image created by a variety of text-to-image models, question, ground-truth answer, textual hint, and attribution. Human evaluation reveals that existing models lag significantly behind human performance, which is at 82\% accuracy, with Gemini-Pro-1.5 leading with 40\% accuracy. Our benchmark comes with automatic evaluation tasks to make assessment scalable. These findings underscore the potential of Visual Riddles as a valuable resource for enhancing vision and language models' capabilities in interpreting complex visual scenarios., Comment: https://visual-riddles.github.io/

Communication network engineering in enterprise environments is traditionally a complex, time-consuming, and error-prone manual process. Most research on network engineering automation has concentrated on configuration synthesis, often overlooking changes in the physical network topology. This paper introduces GeNet, a multimodal co-pilot for enterprise network engineers. GeNet is a novel framework that leverages a large language model (LLM) to streamline network design workflows. It uses visual and textual modalities to interpret and update network topologies and device configurations based on user intents. GeNet was evaluated on enterprise network scenarios adapted from Cisco certification exercises. Our results demonstrate GeNet's ability to interpret network topology images accurately, potentially reducing network engineers' efforts and accelerating network design processes in enterprise environments. Furthermore, we show the importance of precise topology understanding when handling intents that require modifications to the network's topology.

As the number and sophistication of cyber attacks have increased, threat hunting has become a critical aspect of active security, enabling proactive detection and mitigation of threats before they cause significant harm. Open-source cyber threat intelligence (OS-CTI) is a valuable resource for threat hunters, however, it often comes in unstructured formats that require further manual analysis. Previous studies aimed at automating OSCTI analysis are limited since (1) they failed to provide actionable outputs, (2) they did not take advantage of images present in OSCTI sources, and (3) they focused on on-premises environments, overlooking the growing importance of cloud environments. To address these gaps, we propose LLMCloudHunter, a novel framework that leverages large language models (LLMs) to automatically generate generic-signature detection rule candidates from textual and visual OSCTI data. We evaluated the quality of the rules generated by the proposed framework using 12 annotated real-world cloud threat reports. The results show that our framework achieved a precision of 92% and recall of 98% for the task of accurately extracting API calls made by the threat actor and a precision of 99% with a recall of 98% for IoCs. Additionally, 99.18% of the generated detection rule candidates were successfully compiled and converted into Splunk queries.

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false positive rates, a lack of interpretability, and an inability to adapt to evolving system behavior. We introduce RAPID, a novel deep learning-based method for robust APT detection and investigation, leveraging context-aware anomaly detection and alert tracing. By utilizing self-supervised sequence learning and iteratively learned embeddings, our approach effectively adapts to dynamic system behavior. The use of provenance tracing both enriches the alerts and enhances the detection capabilities of our approach. Our extensive evaluation demonstrates RAPID's effectiveness and computational efficiency in real-world scenarios. In addition, RAPID achieves higher precision and recall than state-of-the-art methods, significantly reducing false positives. RAPID integrates contextual information and facilitates a smooth transition from detection to investigation, providing security teams with detailed insights to efficiently address APT threats.

A key challenge associated with Kubernetes configuration files (KCFs) is that they are often highly complex and error-prone, leading to security vulnerabilities and operational setbacks. Rule-based (RB) tools for KCF misconfiguration detection rely on static rule sets, making them inherently limited and unable to detect newly-discovered misconfigurations. RB tools also suffer from misdetection, since mistakes are likely when coding the detection rules. Recent methods for detecting and remediating KCF misconfigurations are limited in terms of their scalability and detection coverage, or due to the fact that they have high expertise requirements and do not offer automated remediation along with misconfiguration detection. Novel approaches that employ LLMs in their pipeline rely on API-based, general-purpose, and mainly commercial models. Thus, they pose security challenges, have inconsistent classification performance, and can be costly. In this paper, we propose GenKubeSec, a comprehensive and adaptive, LLM-based method, which, in addition to detecting a wide variety of KCF misconfigurations, also identifies the exact location of the misconfigurations and provides detailed reasoning about them, along with suggested remediation. When empirically compared with three industry-standard RB tools, GenKubeSec achieved equivalent precision (0.990) and superior recall (0.999). When a random sample of KCFs was examined by a Kubernetes security expert, GenKubeSec's explanations as to misconfiguration localization, reasoning and remediation were 100% correct, informative and useful. To facilitate further advancements in this domain, we share the unique dataset we collected, a unified misconfiguration index we developed for label standardization, our experimentation code, and GenKubeSec itself as an open-source tool.

In a fully managed serverless environment, the cloud service provider is responsible for securing the cloud infrastructure, thereby reducing the operational and maintenance efforts of application developers. However, this environment limits the use of existing cybersecurity frameworks and tools, which reduces observability and situational awareness capabilities (e.g., risk assessment, incident response). In addition, existing security frameworks for serverless applications do not generalize well to all application architectures and usually require adaptation, specialized expertise, etc. for use in fully managed serverless environments. In this paper, we introduce a three-layer security scheme for applications deployed in fully managed serverless environments. The first two layers involve a unique ontology based solely on serverless logs which is used to transform them into a unified application activity knowledge graph. In the third layer, we address the need for observability and situational awareness capabilities by implementing two situational awareness tools that utilizes the graph-based representation: 1) An incident response dashboard that leverages the ontology to visualize and examine application activity logs in the context of cybersecurity alerts. Our user study showed that the dashboard enabled participants to respond more accurately and quickly to new security alerts than the baseline tool. 2) A criticality of asset (CoA) risk assessment framework that enables efficient expert-based prioritization in cybersecurity contexts.

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer's codebase. While beneficial, the use of these tools can inadvertently expose the developer's proprietary code to the code assistant service provider during the development process. In this work, we propose a method to mitigate the risk of code leakage when using LLM-based code assistants. CodeCloak is a novel deep reinforcement learning agent that manipulates the prompts before sending them to the code assistant service. CodeCloak aims to achieve the following two contradictory goals: (i) minimizing code leakage, while (ii) preserving relevant and useful suggestions for the developer. Our evaluation, employing StarCoder and Code Llama, LLM-based code assistants models, demonstrates CodeCloak's effectiveness on a diverse set of code repositories of varying sizes, as well as its transferability across different models. We also designed a method for reconstructing the developer's original codebase from code segments sent to the code assistant service (i.e., prompts) during the development process, to thoroughly analyze code leakage risks and evaluate the effectiveness of CodeCloak under practical development scenarios.

Security by design, Sbd is a concept for developing and maintaining systems that are, to the greatest extent possible, free from security vulnerabilities and impervious to security attacks. In addition to technical aspects, such as how to develop a robust industrial control systems hardware, software, communication product, etc., SbD includes also soft aspects, such as organizational managerial attitude and behavior, and employee awareness. Under the Sbd concept, systems, ICS in our context, will be considered more trustworthy by users. User's trust in the systems will be derived from the meticulous adherence to the SbD processes and policies. In accordance with the SbD concept, security is considered. Security measures are implemented, at every stage of the product and systems development life cycle, rather than afterwards. This document presents the security requirements for the implementation of the SbD in industrial control systems. The information presented does not negate any existing security and cyber security standards, etc. Instead, we strongly recommend that organizations should implement and comply with those standards and best practices. Security by design is not a one-time process. It starts at the very beginning of the products of the system design and continues through all its lifecycle. Due to the benefits of the SbD, higher level of security, and robustness to cyber attacks, all organizations associated with the energy sector should strive to establish an ecosystem. The requirements presented in this document may be perceived as burdensome by organizations. However, strict compliance with the requirements and existing security standards and best practices, including continuous monitoring, as specified in this document, is essential to realize an ecosystem driven and protected by the SbD, Comment: 66 pages, 2 figures

Vision transformers have contributed greatly to advancements in the computer vision domain, demonstrating state-of-the-art performance in diverse tasks (e.g., image classification, object detection). However, their high computational requirements grow quadratically with the number of tokens used. Token sparsification mechanisms have been proposed to address this issue. These mechanisms employ an input-dependent strategy, in which uninformative tokens are discarded from the computation pipeline, improving the model's efficiency. However, their dynamism and average-case assumption makes them vulnerable to a new threat vector - carefully crafted adversarial examples capable of fooling the sparsification mechanism, resulting in worst-case performance. In this paper, we present DeSparsify, an attack targeting the availability of vision transformers that use token sparsification mechanisms. The attack aims to exhaust the operating system's resources, while maintaining its stealthiness. Our evaluation demonstrates the attack's effectiveness on three token sparsification mechanisms and examines the attack's transferability between them and its effect on the GPU resources. To mitigate the impact of the attack, we propose various countermeasures., Comment: 18 pages, 6 figures

In recent years, there has been a significant trend in deep neural networks (DNNs), particularly transformer-based models, of developing ever-larger and more capable models. While they demonstrate state-of-the-art performance, their growing scale requires increased computational resources (e.g., GPUs with greater memory capacity). To address this problem, quantization techniques (i.e., low-bit-precision representation and matrix multiplication) have been proposed. Most quantization techniques employ a static strategy in which the model parameters are quantized, either during training or inference, without considering the test-time sample. In contrast, dynamic quantization techniques, which have become increasingly popular, adapt during inference based on the input provided, while maintaining full-precision performance. However, their dynamic behavior and average-case performance assumption makes them vulnerable to a novel threat vector -- adversarial attacks that target the model's efficiency and availability. In this paper, we present QuantAttack, a novel attack that targets the availability of quantized models, slowing down the inference, and increasing memory usage and energy consumption. We show that carefully crafted adversarial examples, which are designed to exhaust the resources of the operating system, can trigger worst-case performance. In our experiments, we demonstrate the effectiveness of our attack on vision transformers on a wide range of tasks, both uni-modal and multi-modal. We also examine the effect of different attack variants (e.g., a universal perturbation) and the transferability between different models.

Satellite systems are facing an ever-increasing amount of cybersecurity threats as their role in communications, navigation, and other services expands. Recent papers have examined attacks targeting satellites and space systems; however, they did not comprehensively analyze the threats to satellites and systematically identify adversarial techniques across the attack lifecycle. This paper presents a comprehensive taxonomy of adversarial tactics, techniques, and procedures explicitly targeting LEO satellites. First, we analyze the space ecosystem including the ground, space, Communication, and user segments, highlighting their architectures, functions, and vulnerabilities. Then, we examine the threat landscape, including adversary types, and capabilities, and survey historical and recent attacks such as jamming, spoofing, and supply chain. Finally, we propose a novel extension of the MITRE ATT&CK framework to categorize satellite attack techniques across the adversary lifecycle from reconnaissance to impact. The taxonomy is demonstrated by modeling high-profile incidents, including the Viasat attack that disrupted Ukraine's communications. The taxonomy provides the foundation for the development of defenses against emerging cyber risks to space assets. The proposed threat model will advance research in the space domain and contribute to the security of the space domain against sophisticated attacks.

In recent years, financial fraud detection systems have become very efficient at detecting fraud, which is a major threat faced by e-commerce platforms. Such systems often include machine learning-based algorithms aimed at detecting and reporting fraudulent activity. In this paper, we examine the application of adversarial learning based ranking techniques in the fraud detection domain and propose FRAUDability, a method for the estimation of a financial fraud detection system's performance for every user. We are motivated by the assumption that "not all users are created equal" -- while some users are well protected by fraud detection algorithms, others tend to pose a challenge to such systems. The proposed method produces scores, namely "fraudability scores," which are numerical estimations of a fraud detection system's ability to detect financial fraud for a specific user, given his/her unique activity in the financial system. Our fraudability scores enable those tasked with defending users in a financial platform to focus their attention and resources on users with high fraudability scores to better protect them. We validate our method using a real e-commerce platform's dataset and demonstrate the application of fraudability scores from the attacker's perspective, on the platform, and more specifically, on the fraud detection systems used by the e-commerce enterprise. We show that the scores can also help attackers increase their financial profit by 54%, by engaging solely with users with high fraudability scores, avoiding those users whose spending habits enable more accurate fraud detection.

Security orchestration, automation, and response (SOAR) systems ingest alerts from security information and event management (SIEM) system, and then trigger relevant playbooks that automate and orchestrate the execution of a sequence of security activities. SOAR systems have two major limitations: (i) security analysts need to define, create and change playbooks manually, and (ii) the choice between multiple playbooks that could be triggered is based on rules defined by security analysts. To address these limitations, recent studies in the field of artificial intelligence for cybersecurity suggested the task of interactive playbook creation. In this paper, we propose IC-SECURE, an interactive playbook creation solution based on a novel deep learning-based approach that provides recommendations to security analysts during the playbook creation process. IC-SECURE captures the context in the form of alert data and current status of incomplete playbook, required to make reasonable recommendation for next module that should be included in the new playbook being created. We created three evaluation datasets, each of which involved a combination of a set of alert rules and a set of playbooks from a SOAR platform. We evaluated IC-SECURE under various settings, and compared our results with two state-of-the-art recommender system methods. In our evaluation IC-SECURE demonstrated superior performance compared to other methods by consistently recommending the correct security module, achieving precision@1 > 0.8 and recall@3 > 0.92

The Unified Extensible Firmware Interface (UEFI) is a linchpin of modern computing systems, governing secure system initialization and booting. This paper is urgently needed because of the surge in UEFI-related attacks and vulnerabilities in recent years. Motivated by this urgent concern, we undertake an extensive exploration of the UEFI landscape, dissecting its distribution supply chain, booting process, and security features. We carefully study a spectrum of UEFI-targeted attacks and proofs of concept (PoCs) for exploiting UEFI-related vulnerabilities. Building upon these insights, we construct a comprehensive attack threat model encompassing threat actors, attack vectors, attack types, vulnerabilities, attack capabilities, and attacker objectives. Drawing inspiration from the MITRE ATT&CK framework, we present a MITRE ATT&CK-like taxonomy delineating tactics, techniques, and sub-techniques in the context of UEFI attacks. This taxonomy can provide a road map for identifying existing gaps and developing new techniques for rootkit prevention, detection, and removal. Finally, the paper discusses existing countermeasures against UEFI attacks including a variety of technical and operational measures that can be implemented to lower the risk of UEFI attacks to an acceptable level. This paper seeks to clarify the complexities of UEFI and equip the cybersecurity community with the necessary knowledge to strengthen the security of this critical component against a growing threat landscape.

Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess the ability to query the model and observe its outputs (e.g., labels). In this work, we demonstrate, for the first time, the ability to enhance such decision-based attacks. To accomplish this, we present an approach that exploits a novel side channel in which the adversary simply measures the execution time of the algorithm used to post-process the predictions of the ML model under attack. The leakage of inference-state elements into algorithmic timing side channels has never been studied before, and we have found that it can contain rich information that facilitates superior timing attacks that significantly outperform attacks based solely on label outputs. In a case study, we investigate leakage from the non-maximum suppression (NMS) algorithm, which plays a crucial role in the operation of object detectors. In our examination of the timing side-channel vulnerabilities associated with this algorithm, we identified the potential to enhance decision-based attacks. We demonstrate attacks against the YOLOv3 detector, leveraging the timing leakage to successfully evade object detection using adversarial examples, and perform dataset inference. Our experiments show that our adversarial examples exhibit superior perturbation quality compared to a decision-based attack. In addition, we present a new threat model in which dataset inference based solely on timing leakage is performed. To address the timing leakage vulnerability inherent in the NMS algorithm, we explore the potential and limitations of implementing constant-time inference passes as a mitigation strategy.

Object detection models, which are widely used in various domains (such as retail), have been shown to be vulnerable to adversarial attacks. Existing methods for detecting adversarial attacks on object detectors have had difficulty detecting new real-life attacks. We present X-Detect, a novel adversarial patch detector that can: i) detect adversarial samples in real time, allowing the defender to take preventive action; ii) provide explanations for the alerts raised to support the defender's decision-making process, and iii) handle unfamiliar threats in the form of new attacks. Given a new scene, X-Detect uses an ensemble of explainable-by-design detectors that utilize object extraction, scene manipulation, and feature transformation techniques to determine whether an alert needs to be raised. X-Detect was evaluated in both the physical and digital space using five different attack scenarios (including adaptive attacks) and the COCO dataset and our new Superstore dataset. The physical evaluation was performed using a smart shopping cart setup in real-world settings and included 17 adversarial patch attacks recorded in 1,700 adversarial videos. The results showed that X-Detect outperforms the state-of-the-art methods in distinguishing between benign and adversarial scenes for all attack scenarios while maintaining a 0% FPR (no false alarms) and providing actionable explanations for the alerts raised. A demo is available.

Weird, unusual, and uncanny images pique the curiosity of observers because they challenge commonsense. For example, an image released during the 2022 world cup depicts the famous soccer stars Lionel Messi and Cristiano Ronaldo playing chess, which playfully violates our expectation that their competition should occur on the football field. Humans can easily recognize and interpret these unconventional images, but can AI models do the same? We introduce WHOOPS!, a new dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. We consider several tasks posed over the dataset. In addition to image captioning, cross-modal matching, and visual question answering, we introduce a difficult explanation generation task, where models must identify and explain why a given image is unusual. Our results show that state-of-the-art models such as GPT3 and BLIP2 still lag behind human performance on WHOOPS!. We hope our dataset will inspire the development of AI models with stronger visual commonsense reasoning abilities. Data, models and code are available at the project website: whoops-benchmark.github.io, Comment: Accepted to ICCV 2023. Website: whoops-benchmark.github.io

Attack vectors for adversaries have increased in organizations because of the growing use of less secure IoT devices. The risk of attacks on an organization's network has also increased due to the bring your own device (BYOD) policy which permits employees to bring IoT devices onto the premises and attach them to the organization's network. To tackle this threat and protect their networks, organizations generally implement security policies in which only white listed IoT devices are allowed on the organization's network. To monitor compliance with such policies, it has become essential to distinguish IoT devices permitted within an organization's network from non white listed (unknown) IoT devices. In this research, deep learning is applied to network communication for the automated identification of IoT devices permitted on the network. In contrast to existing methods, the proposed approach does not require complex feature engineering of the network communication, because the 'communication behavior' of IoT devices is represented as small images which are generated from the device's network communication payload. The proposed approach is applicable for any IoT device, regardless of the protocol used for communication. As our approach relies on the network communication payload, it is also applicable for the IoT devices behind a network address translation (NAT) enabled router. In this study, we trained various classifiers on a publicly accessible dataset to identify IoT devices in different scenarios, including the identification of known and unknown IoT devices, achieving over 99% overall average detection accuracy., Comment: J Ambient Intell Human Comput (2022)

Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task, a more common real-world use case, remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) in images that contain multiple objects belonging to different class categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets., Comment: 10 pages, 6 figures

Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks. However, since complex classification models produce superior performance when trained on low-level (or encoded) features, in many cases, the explanations generated by these algorithms are neither interpretable nor usable by humans. Methods proposed in recent studies that support the generation of human-interpretable explanations are impractical, because they require a fully invertible transformation function that maps the model's input features to the human-interpretable features. In this work, we introduce Latent SHAP, a black-box feature attribution framework that provides human-interpretable explanations, without the requirement for a fully invertible transformation function. We demonstrate Latent SHAP's effectiveness using (1) a controlled experiment where invertible transformation functions are available, which enables robust quantitative evaluation of our method, and (2) celebrity attractiveness classification (using the CelebA dataset) where invertible transformation functions are not available, which enables thorough qualitative evaluation of our method.

In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this paper, we present an adaptive framework to watermark a protected model, leveraging the unique behavior present in the model due to a unique random seed initialized during the model training. This watermark is used to detect extracted models, which have the same unique behavior, indicating an unauthorized usage of the protected model's intellectual property (IP). First, we show how an initial seed for random number generation as part of model training produces distinct characteristics in the model's decision boundaries, which are inherited by extracted models and present in their decision boundaries, but aren't present in non-extracted models trained on the same data-set with a different seed. Based on our findings, we suggest the Robust Adaptive Watermarking (RAW) Framework, which utilizes the unique behavior present in the protected and extracted models to generate a watermark key-set and verification model. We show that the framework is robust to (1) unseen model extraction attacks, and (2) extracted models which undergo a blurring method (e.g., weight pruning). We evaluate the framework's robustness against a naive attacker (unaware that the model is watermarked), and an informed attacker (who employs blurring strategies to remove watermarked behavior from an extracted model), and achieve outstanding (i.e., >0.9) AUC values. Finally, we show that the framework is robust to model extraction attacks with different structure and/or architecture than the protected model., Comment: 9 pages, 6 figures, 3 tables

Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predictions by placing a patch containing an adversarial pattern on the target object or anywhere within the frame. However, none of prior research proposed a misclassification attack on ODs, in which the patch is applied on the target object. In this study, we propose a novel, universal, targeted, label-switch attack against the state-of-the-art object detector, YOLO. In our attack, we use (i) a tailored projection function to enable the placement of the adversarial patch on multiple target objects in the image (e.g., cars), each of which may be located a different distance away from the camera or have a different view angle relative to the camera, and (ii) a unique loss function capable of changing the label of the attacked objects. The proposed universal patch, which is trained in the digital domain, is transferable to the physical domain. We performed an extensive evaluation using different types of object detectors, different video streams captured by different cameras, and various target classes, and evaluated different configurations of the adversarial patch in the physical domain.

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target model. Until now, the prevalent method to ascertain success has been trial and error-testing crafted samples directly on the victim model. This approach, however, risks detection with every attempt, forcing attackers to either perfect their first try or face exposure. Our paper introduces a ranking strategy that refines the transfer attack process, enabling the attacker to estimate the likelihood of success without repeated trials on the victim's system. By leveraging a set of diverse surrogate models, our method can predict transferability of adversarial examples. This strategy can be used to either select the best sample to use in an attack or the best perturbation to apply to a specific sample. Using our strategy, we were able to raise the transferability of adversarial examples from a mere 20% - akin to random selection-up to near upper-bound levels, with some scenarios even witnessing a 100% success rate. This substantial improvement not only sheds light on the shared susceptibilities across diverse architectures but also demonstrates that attackers can forego the detectable trial-and-error tactics raising increasing the threat of surrogate-based attacks.

While vision-and-language models perform well on tasks such as visual question answering, they struggle when it comes to basic human commonsense reasoning skills. In this work, we introduce WinoGAViL: an online game of vision-and-language associations (e.g., between werewolves and a full moon), used as a dynamic evaluation benchmark. Inspired by the popular card game Codenames, a spymaster gives a textual cue related to several visual candidates, and another player tries to identify them. Human players are rewarded for creating associations that are challenging for a rival AI model but still solvable by other human players. We use the game to collect 3.5K instances, finding that they are intuitive for humans (>90% Jaccard index) but challenging for state-of-the-art AI models, where the best model (ViLT) achieves a score of 52%, succeeding mostly where the cue is visually salient. Our analysis as well as the feedback we collect from players indicate that the collected associations require diverse reasoning skills, including general knowledge, common sense, abstraction, and more. We release the dataset, the code and the interactive game, allowing future data collection that can be used to develop models with better association abilities., Comment: Accepted to NeurIPS 2022, Datasets and Benchmarks. Website: https://winogavil.github.io/

The ability to detect whether an object is a 2D or 3D object is extremely important in autonomous driving, since a detection error can have life-threatening consequences, endangering the safety of the driver, passengers, pedestrians, and others on the road. Methods proposed to distinguish between 2 and 3D objects (e.g., liveness detection methods) are not suitable for autonomous driving, because they are object dependent or do not consider the constraints associated with autonomous driving (e.g., the need for real-time decision-making while the vehicle is moving). In this paper, we present EyeDAS, a novel few-shot learning-based method aimed at securing an object detector (OD) against the threat posed by the stereoblindness syndrome (i.e., the inability to distinguish between 2D and 3D objects). We evaluate EyeDAS's real-time performance using 2,000 objects extracted from seven YouTube video recordings of street views taken by a dash cam from the driver's seat perspective. When applying EyeDAS to seven state-of-the-art ODs as a countermeasure, EyeDAS was able to reduce the 2D misclassification rate from 71.42-100% to 2.4% with a 3D misclassification rate of 0% (TPR of 1.0). We also show that EyeDAS outperforms the baseline method and achieves an AUC of over 0.999 and a TPR of 1.0 with an FPR of 0.024.

User feedback is one of the most effective methods to build and maintain trust in electronic commerce platforms. Unfortunately, dishonest sellers often bend over backward to manipulate users' feedback or place phony bids in order to increase their own sales and harm competitors. The black market of user feedback, supported by a plethora of shill bidders, prospers on top of legitimate electronic commerce. In this paper, we investigate the ecosystem of shill bidders based on large-scale data by analyzing hundreds of millions of users who performed billions of transactions, and we propose a machine-learning-based method for identifying communities of users that methodically provide dishonest feedback. Our results show that (1) shill bidders can be identified with high precision based on their transaction and feedback statistics; and (2) in contrast to legitimate buyers and sellers, shill bidders form cliques to support each other.

In this paper, we present bAdvertisement, a novel attack method against advanced driver-assistance systems (ADASs). bAdvertisement is performed as a supply chain attack via a compromised computer in a printing house, by embedding a "phantom" object in a print advertisement. When the compromised print advertisement is observed by an ADAS in a passing car, an undesired reaction is triggered from the ADAS. We analyze state-of-the-art object detectors and show that they do not take color or context into account in object detection. Our validation of these findings on Mobileye 630 PRO shows that this ADAS also fails to take color or context into account. Then, we show how an attacker can take advantage of these findings to execute an attack on a commercial ADAS, by embedding a phantom road sign in a print advertisement, which causes a car equipped with Mobileye 630 PRO to trigger a false notification to slow down. Finally, we discuss multiple countermeasures which can be deployed in order to mitigate the effect of our proposed attack.

MIL-STD-1553, a standard that defines a communication bus for interconnected devices, is widely used in military and aerospace avionic platforms. Due to its lack of security mechanisms, MIL-STD-1553 is exposed to cyber threats. The methods previously proposed to address these threats are very limited, resulting in the need for more advanced techniques. Inspired by the defense in depth principle, we propose AnoMili, a novel protection system for the MIL-STD-1553 bus, which consists of: (i) a physical intrusion detection mechanism that detects unauthorized devices connected to the 1553 bus, even if they are passive (sniffing), (ii) a device fingerprinting mechanism that protects against spoofing attacks (two approaches are proposed: prevention and detection), (iii) a context-based anomaly detection mechanism, and (iv) an anomaly explanation engine responsible for explaining the detected anomalies in real time. We evaluate AnoMili's effectiveness and practicability in two real 1553 hardware-based testbeds. The effectiveness of the anomaly explanation engine is also demonstrated. All of the detection and prevention mechanisms employed had high detection rates (over 99.45%) with low false positive rates. The context-based anomaly detection mechanism obtained perfect results when evaluated on a dataset used in prior work.

Deep learning has shown great promise in the domain of medical image analysis. Medical professionals and healthcare providers have been adopting the technology to speed up and enhance their work. These systems use deep neural networks (DNN) which are vulnerable to adversarial samples; images with imperceivable changes that can alter the model's prediction. Researchers have proposed defences which either make a DNN more robust or detect the adversarial samples before they do harm. However, none of these works consider an informed attacker which can adapt to the defence mechanism. We show that an informed attacker can evade five of the current state of the art defences while successfully fooling the victim's deep learning model, rendering these defences useless. We then suggest better alternatives for securing healthcare DNNs from such attacks: (1) harden the system's security and (2) use digital signatures.

O-RAN is a new, open, adaptive, and intelligent RAN architecture. Motivated by the success of artificial intelligence in other domains, O-RAN strives to leverage machine learning (ML) to automatically and efficiently manage network resources in diverse use cases such as traffic steering, quality of experience prediction, and anomaly detection. Unfortunately, it has been shown that ML-based systems are vulnerable to an attack technique referred to as adversarial machine learning (AML). This special kind of attack has already been demonstrated in recent studies and in multiple domains. In this paper, we present a systematic AML threat analysis for O-RAN. We start by reviewing relevant ML use cases and analyzing the different ML workflow deployment scenarios in O-RAN. Then, we define the threat model, identifying potential adversaries, enumerating their adversarial capabilities, and analyzing their main goals. Next, we explore the various AML threats associated with O-RAN and review a large number of attacks that can be performed to realize these threats and demonstrate an AML attack on a traffic steering model. In addition, we analyze and propose various AML countermeasures for mitigating the identified threats. Finally, based on the identified AML threats and countermeasures, we present a methodology and a tool for performing risk assessment for AML attacks for a specific ML use case in O-RAN.

The Open Radio Access Network (O-RAN) is a promising RAN architecture, aimed at reshaping the RAN industry toward an open, adaptive, and intelligent RAN. In this paper, we conducted a comprehensive security analysis of Open Radio Access Networks (O-RAN). Specifically, we review the architectural blueprint designed by the O-RAN alliance -- A leading force in the cellular ecosystem. Within the security analysis, we provide a detailed overview of the O-RAN architecture; present an ontology for evaluating the security of a system, which is currently at an early development stage; detect the primary risk areas to O-RAN; enumerate the various threat actors to O-RAN; and model potential threats to O-RAN. The significance of this work is providing an updated attack surface to cellular network operators. Based on the attack surface, cellular network operators can carefully deploy the appropriate countermeasure for increasing the security of O-RAN.

In this study, we propose an innovative method for the real-time detection of GPS spoofing attacks targeting drones, based on the video stream captured by a drone's camera. The proposed method collects frames from the video stream and their location (GPS); by calculating the correlation between each frame, our method can identify an attack on a drone. We first analyze the performance of the suggested method in a controlled environment by conducting experiments on a flight simulator that we developed. Then, we analyze its performance in the real world using a DJI drone. Our method can provide different levels of security against GPS spoofing attacks, depending on the detection interval required; for example, it can provide a high level of security to a drone flying at an altitude of 50-100 meters over an urban area at an average speed of 4 km/h in conditions of low ambient light; in this scenario, the method can provide a level of security that detects any GPS spoofing attack in which the spoofed location is a distance of 1-4 meters (an average of 2.5 meters) from the real location., Comment: 8 pages, 16 figures

Deep learning-based facial recognition (FR) models have demonstrated state-of-the-art performance in the past few years, even when wearing protective medical face masks became commonplace during the COVID-19 pandemic. Given the outstanding performance of these models, the machine learning research community has shown increasing interest in challenging their robustness. Initially, researchers presented adversarial attacks in the digital domain, and later the attacks were transferred to the physical domain. However, in many cases, attacks in the physical domain are conspicuous, and thus may raise suspicion in real-world environments (e.g., airports). In this paper, we propose Adversarial Mask, a physical universal adversarial perturbation (UAP) against state-of-the-art FR models that is applied on face masks in the form of a carefully crafted pattern. In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets. In addition, we validated our adversarial mask's effectiveness in real-world experiments (CCTV use case) by printing the adversarial pattern on a fabric face mask. In these experiments, the FR system was only able to identify 3.34% of the participants wearing the mask (compared to a minimum of 83.34% with other evaluated masks). A demo of our experiments can be found at: https://youtu.be/_TXkDO5z11w., Comment: 16 pages, 9 figures

Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply by training on a non-overlapping set of classes. This can be largely attributed to the differences in their mechanisms as compared to conventional deep networks. However, this also offers new opportunities for novel attackers to induce integrity attacks against such models, which are not present in other machine learning setups. In this work, we aim to close this gap by studying a conceptually simple approach to defend few-shot classifiers against adversarial attacks. More specifically, we propose a simple attack-agnostic detection method, using the concept of self-similarity and filtering, to flag out adversarial support sets which destroy the understanding of a victim classifier for a certain class. Our extended evaluation on the miniImagenet (MI) and CUB datasets exhibit good attack detection performance, across three different few-shot classifiers and across different attack strengths, beating baselines. Our observed results allow our approach to establishing itself as a strong detection method for support set poisoning attacks. We also show that our approach constitutes a generalizable concept, as it can be paired with other filtering functions. Finally, we provide an analysis of our results when we vary two components found in our detection approach., Comment: arXiv admin note: text overlap with arXiv:2012.06330

Deep learning face recognition models are used by state-of-the-art surveillance systems to identify individuals passing through public areas (e.g., airports). Previous studies have demonstrated the use of adversarial machine learning (AML) attacks to successfully evade identification by such systems, both in the digital and physical domains. Attacks in the physical domain, however, require significant manipulation to the human participant's face, which can raise suspicion by human observers (e.g. airport security officers). In this study, we present a novel black-box AML attack which carefully crafts natural makeup, which, when applied on a human participant, prevents the participant from being identified by facial recognition models. We evaluated our proposed attack against the ArcFace face recognition model, with 20 participants in a real-world setup that includes two cameras, different shooting angles, and different lighting conditions. The evaluation results show that in the digital domain, the face recognition system was unable to identify all of the participants, while in the physical domain, the face recognition system was able to identify the participants in only 1.22% of the frames (compared to 47.57% without makeup and 33.73% with random natural makeup), which is below a reasonable threshold of a realistic operational environment.

Although cyberattacks on machine learning (ML) production systems can be harmful, today, security practitioners are ill equipped, lacking methodologies and tactical tools that would allow them to analyze the security risks of their ML-based systems. In this paper, we performed a comprehensive threat analysis of ML production systems. In this analysis, we follow the ontology presented by NIST for evaluating enterprise network security risk and apply it to ML-based production systems. Specifically, we (1) enumerate the assets of a typical ML production system, (2) describe the threat model (i.e., potential adversaries, their capabilities, and their main goal), (3) identify the various threats to ML systems, and (4) review a large number of attacks, demonstrated in previous studies, which can realize these threats. In addition, to quantify the risk of adversarial machine learning (AML) threat, we introduce a novel scoring system, which assign a severity score to different AML attacks. The proposed scoring system utilizes the analytic hierarchy process (AHP) for ranking, with the assistance of security experts, various attributes of the attacks. Finally, we developed an extension to the MulVAL attack graph generation and analysis framework to incorporate cyberattacks on ML production systems. Using the extension, security practitioners can apply attack graph analysis methods in environments that include ML components; thus, providing security practitioners with a methodological and practical tool for evaluating the impact and quantifying the risk of a cyberattack targeting an ML production system.

AI has provided us with the ability to automate tasks, extract information from vast amounts of data, and synthesize media that is nearly indistinguishable from the real thing. However, positive tools can also be used for negative purposes. In particular, cyber adversaries can use AI (such as machine learning) to enhance their attacks and expand their campaigns. Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations. For example, how does an AI-capable adversary impact the cyber kill chain? Does AI benefit the attacker more than the defender? What are the most significant AI threats facing organizations today and what will be their impact on the future? In this survey, we explore the threat of offensive AI on organizations. First, we present the background and discuss how AI changes the adversary's methods, strategies, goals, and overall attack model. Then, through a literature review, we identify 33 offensive AI capabilities which adversaries can use to enhance their attacks. Finally, through a user study spanning industry and academia, we rank the AI threats and provide insights on the adversaries.

The Controller Area Network (CAN) is used for communication between in-vehicle devices. The CAN bus has been shown to be vulnerable to remote attacks. To harden vehicles against such attacks, vehicle manufacturers have divided in-vehicle networks into sub-networks, logically isolating critical devices. However, attackers may still have physical access to various sub-networks where they can connect a malicious device. This threat has not been adequately addressed, as methods proposed to determine physical intrusion points have shown weak results, emphasizing the need to develop more advanced techniques. To address this type of threat, we propose a security hardening system for in-vehicle networks. The proposed system includes two mechanisms that process deep features extracted from voltage signals measured on the CAN bus. The first mechanism uses data augmentation and deep learning to detect and locate physical intrusions when the vehicle starts; this mechanism can detect and locate intrusions, even when the connected malicious devices are silent. This mechanism's effectiveness (100% accuracy) is demonstrated in a wide variety of insertion scenarios on a CAN bus prototype. The second mechanism is a continuous device authentication mechanism, which is also based on deep learning; this mechanism's robustness (99.8% accuracy) is demonstrated on a real moving vehicle.

Radar systems are mainly used for tracking aircraft, missiles, satellites, and watercraft. In many cases, information regarding the objects detected by the radar system is sent to, and used by, a peripheral consuming system, such as a missile system or a graphical user interface used by an operator. Those systems process the data stream and make real-time, operational decisions based on the data received. Given this, the reliability and availability of information provided by radar systems has grown in importance. Although the field of cyber security has been continuously evolving, no prior research has focused on anomaly detection in radar systems. In this paper, we present a deep learning-based method for detecting anomalies in radar system data streams. We propose a novel technique which learns the correlation between numerical features and an embedding representation of categorical features in an unsupervised manner. The proposed technique, which allows the detection of malicious manipulation of critical fields in the data stream, is complemented by a timing-interval anomaly detection mechanism proposed for the detection of message dropping attempts. Real radar system data is used to evaluate the proposed method. Our experiments demonstrate the method's high detection accuracy on a variety of data stream manipulation attacks (average detection rate of 88% with 1.59% false alarms) and message dropping attacks (average detection rate of 92% with 2.2% false alarms).

Adversarial transferability, namely the ability of adversarial perturbations to simultaneously fool multiple learning models, has long been the "big bad wolf" of adversarial machine learning. Successful transferability-based attacks requiring no prior knowledge of the attacked model's parameters or training data have been demonstrated numerous times in the past, implying that machine learning models pose an inherent security threat to real-life systems. However, all of the research performed in this area regarded transferability as a probabilistic property and attempted to estimate the percentage of adversarial examples that are likely to mislead a target model given some predefined evaluation set. As a result, those studies ignored the fact that real-life adversaries are often highly sensitive to the cost of a failed attack. We argue that overlooking this sensitivity has led to an exaggerated perception of the transferability threat, when in fact real-life transferability-based attacks are quite unlikely. By combining theoretical reasoning with a series of empirical results, we show that it is practically impossible to predict whether a given adversarial example is transferable to a specific target model in a black-box setting, hence questioning the validity of adversarial transferability as a real-life attack tool for adversaries that are sensitive to the cost of a failed attack.

Network intrusion attacks are a known threat. To detect such attacks, network intrusion detection systems (NIDSs) have been developed and deployed. These systems apply machine learning models to high-dimensional vectors of features extracted from network traffic to detect intrusions. Advances in NIDSs have made it challenging for attackers, who must execute attacks without being detected by these systems. Prior research on bypassing NIDSs has mainly focused on perturbing the features extracted from the attack traffic to fool the detection system, however, this may jeopardize the attack's functionality. In this work, we present TANTRA, a novel end-to-end Timing-based Adversarial Network Traffic Reshaping Attack that can bypass a variety of NIDSs. Our evasion attack utilizes a long short-term memory (LSTM) deep neural network (DNN) which is trained to learn the time differences between the target network's benign packets. The trained LSTM is used to set the time differences between the malicious traffic packets (attack), without changing their content, such that they will "behave" like benign network traffic and will not be detected as an intrusion. We evaluate TANTRA on eight common intrusion attacks and three state-of-the-art NIDS systems, achieving an average success rate of 99.99\% in network intrusion detection system evasion. We also propose a novel mitigation technique to address this new evasion attack.

Adversarial examples have proven to be a concerning threat to deep learning models, particularly in the image domain. However, while many studies have examined adversarial examples in the real world, most of them relied on 2D photos of the attack scene. As a result, the attacks proposed may have limited effectiveness when implemented in realistic environments with 3D objects or varied conditions. There are few studies on adversarial learning that use 3D objects, and in many cases, other researchers are unable to replicate the real-world evaluation process. In this study, we present a framework that uses 3D modeling to craft adversarial patches for an existing real-world scene. Our approach uses a 3D digital approximation of the scene as a simulation of the real world. With the ability to add and manipulate any element in the digital scene, our framework enables the attacker to improve the adversarial patch's impact in real-world settings. We use the framework to create a patch for an everyday scene and evaluate its performance using a novel evaluation process that ensures that our results are reproducible in both the digital space and the real world. Our evaluation results show that the framework can generate adversarial patches that are robust to different settings in the real world.

The need to detect bias in machine learning (ML) models has led to the development of multiple bias detection methods, yet utilizing them is challenging since each method: i) explores a different ethical aspect of bias, which may result in contradictory output among the different methods, ii) provides an output of a different range/scale and therefore, can't be compared with other methods, and iii) requires different input, and therefore a human expert needs to be involved to adjust each method according to the examined model. In this paper, we present BENN -- a novel bias estimation method that uses a pretrained unsupervised deep neural network. Given a ML model and data samples, BENN provides a bias estimation for every feature based on the model's predictions. We evaluated BENN using three benchmark datasets and one proprietary churn prediction model used by a European Telco and compared it with an ensemble of 21 existing bias estimation methods. Evaluation results highlight the significant advantages of BENN over the ensemble, as it is generic (i.e., can be applied to any ML model) and there is no need for a domain expert, yet it provides bias estimations that are aligned with those of the ensemble.

Physical adversarial attacks against object detectors have seen increasing success in recent years. However, these attacks require direct access to the object of interest in order to apply a physical patch. Furthermore, to hide multiple objects, an adversarial patch must be applied to each object. In this paper, we propose a contactless translucent physical patch containing a carefully constructed pattern, which is placed on the camera's lens, to fool state-of-the-art object detectors. The primary goal of our patch is to hide all instances of a selected target class. In addition, the optimization method used to construct the patch aims to ensure that the detection of other (untargeted) classes remains unharmed. Therefore, in our experiments, which are conducted on state-of-the-art object detection models used in autonomous driving, we study the effect of the patch on the detection of both the selected target class and the other classes. We show that our patch was able to prevent the detection of 42.27% of all stop sign instances while maintaining high (nearly 80%) detection of the other classes.

Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers opportunities for novel attacks, such as targeting support sets required to categorise unseen test samples, which are not available in other machine learning setups. In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class. We achieve this by introducing the concept of self-similarity of a support set and by employing filtering of supports. Our method is attack-agnostic, and we are the first to explore adversarial detection for support sets of few-shot classifiers to the best of our knowledge. Our evaluation of the miniImagenet (MI) and CUB datasets exhibits good attack detection performance despite conceptual simplicity, showing high AUROC scores. We show that self-similarity and filtering for adversarial detection can be paired with other filtering functions, constituting a generalisable concept., Comment: Accepted in the International Workshop on Safety and Security of Deep Learning 2021