Search

Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when to prune; and the specifics, defining how to prune. We then highlight the limitations of current empirical analyses and propose a novel, fair evaluation benchmark to address them. We finally conduct an empirical re-evaluation of current adversarial pruning methods and discuss the results, highlighting the shared traits of top-performing adversarial pruning methods, as well as common issues. We welcome contributions in our publicly-available benchmark at https://github.com/pralab/AdversarialPruningBenchmark

Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase. These attacks typically require re-clustering the entire dataset multiple times to generate predictions and assess the attacker's objectives, significantly hindering their scalability. This paper addresses these limitations by proposing Sonic, a novel genetic data poisoning attack that leverages incremental and scalable clustering algorithms, e.g., FISHDBC, as surrogates to accelerate poisoning attacks against graph-based and density-based clustering methods, such as HDBSCAN. We empirically demonstrate the effectiveness and efficiency of Sonic in poisoning the target clustering algorithms. We then conduct a comprehensive analysis of the factors affecting the scalability and transferability of poisoning attacks against clustering algorithms, and we conclude by examining the robustness of hyperparameters in our attack strategy Sonic., Comment: preprint paper

Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size schedulers, and default hyperparameters. In this work, we tackle these limitations by proposing a parametric variation of the well-known fast minimum-norm attack algorithm, whose loss, optimizer, step-size scheduler, and hyperparameters can be dynamically adjusted. We re-evaluate 12 robust models, showing that our attack finds smaller adversarial perturbations without requiring any additional tuning. This also enables reporting adversarial robustness as a function of the perturbation budget, providing a more complete evaluation than that offered by fixed-budget attacks, while remaining efficient. We release our open-source code at https://github.com/pralab/HO-FMN.

ModSecurity is widely recognized as the standard open-source Web Application Firewall (WAF), maintained by the OWASP Foundation. It detects malicious requests by matching them against the Core Rule Set (CRS), identifying well-known attack patterns. Each rule is manually assigned a weight based on the severity of the corresponding attack, and a request is blocked if the sum of the weights of matched rules exceeds a given threshold. However, we argue that this strategy is largely ineffective against web attacks, as detection is only based on heuristics and not customized on the application to protect. In this work, we overcome this issue by proposing a machine-learning model that uses the CRS rules as input features. Through training, ModSec-Learn is able to tune the contribution of each CRS rule to predictions, thus adapting the severity level to the web applications to protect. Our experiments show that ModSec-Learn achieves a significantly better trade-off between detection and false positive rates. Finally, we analyze how sparse regularization can reduce the number of rules that are relevant at inference time, by discarding more than 30% of the CRS rules. We release our open-source code and the dataset at https://github.com/pralab/modsec-learn and https://github.com/pralab/http-traffic-dataset, respectively., Comment: arXiv admin note: text overlap with arXiv:2308.04964

Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks' vulnerability to adversarial example -- input samples crafted ad-hoc to induce a desired misclassification. Relevant literature has claimed contradictory remarks in support of and against the robustness of over-parameterized networks. These contradictory findings might be due to the failure of the attack employed to evaluate the networks' robustness. Previous research has demonstrated that depending on the considered model, the algorithm employed to generate adversarial examples may not function properly, leading to overestimating the model's robustness. In this work, we empirically study the robustness of over-parameterized networks against adversarial examples. However, unlike the previous works, we also evaluate the considered attack's reliability to support the results' veracity. Our results show that over-parameterized networks are robust against adversarial attacks as opposed to their under-parameterized counterparts.

As a result of decades of research, Windows malware detection is approached through a plethora of techniques. However, there is an ongoing mismatch between academia -- which pursues an optimal performances in terms of detection rate and low false alarms -- and the requirements of real-world scenarios. In particular, academia focuses on combining static and dynamic analysis within a single or ensemble of models, falling into several pitfalls like (i) firing dynamic analysis without considering the computational burden it requires; (ii) discarding impossible-to-analyse samples; and (iii) analysing robustness against adversarial attacks without considering that malware detectors are complemented with more non-machine-learning components. Thus, in this paper we propose SLIFER, a novel Windows malware detection pipeline sequentially leveraging both static and dynamic analysis, interrupting computations as soon as one module triggers an alarm, requiring dynamic analysis only when needed. Contrary to the state of the art, we investigate how to deal with samples resistance to analysis, showing how much they impact performances, concluding that it is better to flag them as legitimate to not drastically increase false alarms. Lastly, we perform a robustness evaluation of SLIFER leveraging content-injections attacks, and we show that, counter-intuitively, attacks are blocked more by YARA rules than dynamic analysis due to byte artifacts created while optimizing the adversarial strategy.

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to defend against adversarial EXEmples. However, current randomized smoothing-based defenses are still vulnerable to attacks that inject blocks of adversarial content. In this paper, we introduce a certifiable defense against patch attacks that guarantees, for a given executable and an adversarial patch size, no adversarial EXEmple exist. Our method is inspired by (de)randomized smoothing which provides deterministic robustness certificates. During training, a base classifier is trained using subsets of continguous bytes. At inference time, our defense splits the executable into non-overlapping chunks, classifies each chunk independently, and computes the final prediction through majority voting to minimize the influence of injected content. Furthermore, we introduce a preprocessing step that fixes the size of the sections and headers to a multiple of the chunk size. As a consequence, the injected content is confined to an integer number of chunks without tampering the other chunks containing the real bytes of the input examples, allowing us to extend our certified robustness guarantees to content insertion attacks. We perform an extensive ablation study, by comparing our defense with randomized smoothing-based defenses against a plethora of content manipulation attacks and neural network architectures. Results show that our method exhibits unmatched robustness against strong content-insertion attacks, outperforming randomized smoothing-based defenses in the literature.

Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number of forward and backward calls to the target models. This provides overly-optimistic and even biased evaluations that may unfairly favor one particular attack over the others. In this work, we aim to overcome these limitations by proposing AttackBench, i.e., the first evaluation framework that enables a fair comparison among different attacks. To this end, we first propose a categorization of gradient-based attacks, identifying their main components and differences. We then introduce our framework, which evaluates their effectiveness and efficiency. We measure these characteristics by (i) defining an optimality metric that quantifies how close an attack is to the optimal solution, and (ii) limiting the number of forward and backward queries to the model, such that all attacks are compared within a given maximum query budget. Our extensive experimental analysis compares more than $100$ attack implementations with a total of over $800$ different configurations against CIFAR-10 and ImageNet models, highlighting that only very few attacks outperform all the competing approaches. Within this analysis, we shed light on several implementation issues that prevent many attacks from finding better solutions or running at all. We release AttackBench as a publicly-available benchmark, aiming to continuously update it to include and evaluate novel gradient-based attacks for optimizing adversarial examples., Comment: https://attackbench.github.io

The living-off-the-land (LOTL) offensive methodologies rely on the perpetration of malicious actions through chains of commands executed by legitimate applications, identifiable exclusively by analysis of system logs. LOTL techniques are well hidden inside the stream of events generated by common legitimate activities, moreover threat actors often camouflage activity through obfuscation, making them particularly difficult to detect without incurring in plenty of false alarms, even using machine learning. To improve the performance of models in such an harsh environment, we propose an augmentation framework to enhance and diversify the presence of LOTL malicious activity inside legitimate logs. Guided by threat intelligence, we generate a dataset by injecting attack templates known to be employed in the wild, further enriched by malleable patterns of legitimate activities to replicate the behavior of evasive threat actors. We conduct an extensive ablation study to understand which models better handle our augmented dataset, also manipulated to mimic the presence of model-agnostic evasion and poisoning attacks. Our results suggest that augmentation is needed to maintain high-predictive capabilities, robustness to attack is achieved through specific hardening techniques like adversarial training, and it is possible to deploy near-real-time models with almost-zero false alarms.

Machine-learning models demand for periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly-updated model may commit mistakes that the previous model did not make. Such misclassifications are referred to as negative flips, and experienced by users as a regression of performance. In this work, we show that this problem also affects robustness to adversarial examples, thereby hindering the development of secure model update practices. In particular, when updating a model to improve its adversarial robustness, some previously-ineffective adversarial examples may become misclassified, causing a regression in the perceived security of the system. We propose a novel technique, named robustness-congruent adversarial training, to address this issue. It amounts to fine-tuning a model with adversarial training, while constraining it to retain higher robustness on the adversarial examples that were correctly classified before the update. We show that our algorithm and, more generally, learning with non-regression constraints, provides a theoretically-grounded framework to train consistent estimators. Our experiments on robust models for computer vision confirm that (i) both accuracy and robustness, even if improved after model update, can be affected by negative flips, and (ii) our robustness-congruent adversarial training can mitigate the problem, outperforming competing baseline methods.

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investigate sparse $\ell_1$- and $\ell_0$-norm attacks. In particular, $\ell_0$-norm attacks remain the least studied due to the inherent complexity of optimizing over a non-convex and non-differentiable constraint. However, evaluating adversarial robustness under these attacks could reveal weaknesses otherwise left untested with more conventional $\ell_2$- and $\ell_\infty$-norm attacks. In this work, we propose a novel $\ell_0$-norm attack, called $\sigma$-zero, which leverages a differentiable approximation of the $\ell_0$ norm to facilitate gradient-based optimization, and an adaptive projection operator to dynamically adjust the trade-off between loss minimization and perturbation sparsity. Extensive evaluations using MNIST, CIFAR10, and ImageNet datasets, involving robust and non-robust models, show that $\sigma$-zero finds minimum $\ell_0$-norm adversarial examples without requiring any time-consuming hyperparameter tuning, and that it outperforms all competing sparse attacks in terms of success rate, perturbation size, and efficiency., Comment: Code available at https://github.com/Cinofix/sigma-zero-adversarial-attack

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss function, the optimizer and the step-size scheduler, along with the corresponding hyperparameters. Our extensive evaluation involving several robust models demonstrates the improved efficacy of fast minimum-norm attacks when hyper-up with hyperparameter optimization. We release our open-source code at https://github.com/pralab/HO-FMN., Comment: Accepted at ESANN23

Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that adversarial pruning methods can produce sparse networks while also preserving robustness to adversarial examples. In this work, we first re-evaluate three state-of-the-art adversarial pruning methods, showing that their robustness was indeed overestimated. We then compare pruned and dense versions of the same models, discovering that samples on thin ice, i.e., closer to the unpruned model's decision boundary, are typically misclassified after pruning. We conclude by discussing how this intuition may lead to designing more effective adversarial pruning methods in future work.

Machine-learning phishing webpage detectors (ML-PWD) have been shown to suffer from adversarial manipulations of the HTML code of the input webpage. Nevertheless, the attacks recently proposed have demonstrated limited effectiveness due to their lack of optimizing the usage of the adopted manipulations, and they focus solely on specific elements of the HTML code. In this work, we overcome these limitations by first designing a novel set of fine-grained manipulations which allow to modify the HTML code of the input phishing webpage without compromising its maliciousness and visual appearance, i.e., the manipulations are functionality- and rendering-preserving by design. We then select which manipulations should be applied to bypass the target detector by a query-efficient black-box optimization algorithm. Our experiments show that our attacks are able to raze to the ground the performance of current state-of-the-art ML-PWD using just 30 queries, thus overcoming the weaker attacks developed in previous work, and enabling a much fairer robustness evaluation of ML-PWD., Comment: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security (AISec '23), November 30, 2023, Copenhagen, Denmark

Dynamic analysis enables detecting Windows malware by executing programs in a controlled environment, and storing their actions in log reports. Previous work has started training machine learning models on such reports to perform either malware detection or malware classification. However, most of the approaches (i) have only considered convolutional and long-short term memory networks, (ii) they have been built focusing only on APIs called at runtime, without considering other relevant though heterogeneous sources of information like network and file operations, and (iii) the code and pretrained models are hardly available, hindering reproducibility of results in this research area. In this work, we overcome these limitations by presenting Nebula, a versatile, self-attention transformer-based neural architecture that can generalize across different behavior representations and formats, combining heterogeneous information from dynamic log reports. We show the efficacy of Nebula on three distinct data collections from different dynamic analysis platforms, comparing its performance with previous state-of-the-art models developed for malware detection and classification tasks. We produce an extensive ablation study that showcases how the components of Nebula influence its predictive performance, while enabling it to outperform some competing approaches at very low false positive rates. We conclude our work by inspecting the behavior of Nebula through the application of explainability methods, which highlight that Nebula correctly focuses more on portions of reports that contain malicious activities. We release our code and models at github.com/dtrizna/nebula., Comment: 18 pages, 7 figures, 12 tables, preprint, in review

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial inputs, under the assumption that such attacks exhibit a higher prediction uncertainty than pristine data, it has been shown that adaptive attacks specifically aimed at reducing also the uncertainty estimate can easily bypass this defense mechanism. In this work, we focus on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate, but regardless of the correctness of the prediction; in particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator. Following such direction, we: \textit{(i)} design a threat model for attacks targeting uncertainty quantification; \textit{(ii)} devise different attack strategies on conceptually different UQ techniques spanning for both classification and semantic segmentation problems; \textit{(iii)} conduct a first complete and extensive analysis to compare the differences between some of the most employed UQ approaches under attack. Our extensive experimental analysis shows that our attacks are more effective in manipulating uncertainty quantification measures than attacks aimed to also induce misclassifications.

RGB-D object recognition systems improve their predictive performances by fusing color and depth information, outperforming neural network architectures that rely solely on colors. While RGB-D systems are expected to be more robust to adversarial examples than RGB-only systems, they have also been proven to be highly vulnerable. Their robustness is similar even when the adversarial examples are generated by altering only the original images' colors. Different works highlighted the vulnerability of RGB-D systems; however, there is a lacking of technical explanations for this weakness. Hence, in our work, we bridge this gap by investigating the learned deep representation of RGB-D systems, discovering that color features make the function learned by the network more complex and, thus, more sensitive to small perturbations. To mitigate this problem, we propose a defense based on a detection mechanism that makes RGB-D systems more robust against adversarial examples. We empirically show that this defense improves the performances of RGB-D systems against adversarial examples even when they are computed ad-hoc to circumvent this detection mechanism, and that is also more effective than adversarial training., Comment: Accepted for publication in the Information Sciences journal

ModSecurity is widely recognized as the standard open-source Web Application Firewall (WAF), maintained by the OWASP Foundation. It detects malicious requests by matching them against the Core Rule Set, identifying well-known attack patterns. Each rule in the CRS is manually assigned a weight, based on the severity of the corresponding attack, and a request is detected as malicious if the sum of the weights of the firing rules exceeds a given threshold. In this work, we show that this simple strategy is largely ineffective for detecting SQL injection (SQLi) attacks, as it tends to block many legitimate requests, while also being vulnerable to adversarial SQLi attacks, i.e., attacks intentionally manipulated to evade detection. To overcome these issues, we design a robust machine learning model, named AdvModSec, which uses the CRS rules as input features, and it is trained to detect adversarial SQLi attacks. Our experiments show that AdvModSec, being trained on the traffic directed towards the protected web services, achieves a better trade-off between detection and false positive rates, improving the detection rate of the vanilla version of ModSecurity with CRS by 21%. Moreover, our approach is able to improve its adversarial robustness against adversarial SQLi attacks by 42%, thereby taking a step forward towards building more robust and trustworthy WAFs.

Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption and prediction latency. In this work, we propose EAT, a gradient-based algorithm that aims to reduce energy consumption during model training. To this end, we leverage a differentiable approximation of the $\ell_0$ norm, and use it as a sparse penalty over the training loss. Through our experimental analysis conducted on three datasets and two deep neural networks, we demonstrate that our energy-aware training algorithm EAT is able to train networks with a better trade-off between classification performance and energy efficiency., Comment: 12 pages, 3 figures. Paper accepted at the 22nd International Conference on Image Analysis and Processing (ICIAP) 2023

Reinforcement learning allows machines to learn from their own experience. Nowadays, it is used in safety-critical applications, such as autonomous driving, despite being vulnerable to attacks carefully crafted to either prevent that the reinforcement learning algorithm learns an effective and reliable policy, or to induce the trained agent to make a wrong decision. The literature about the security of reinforcement learning is rapidly growing, and some surveys have been proposed to shed light on this field. However, their categorizations are insufficient for choosing an appropriate defense given the kind of system at hand. In our survey, we do not only overcome this limitation by considering a different perspective, but we also discuss the applicability of state-of-the-art attacks and defenses when reinforcement learning algorithms are used in the context of autonomous driving.

Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to recognize images of animals can be reprogrammed to recognize medical images by embedding an adversarial program in the images provided as inputs. This attack can be perpetrated even if the target model is a black box, supposed that the machine-learning model is provided as a service and the attacker can query the model and collect its outputs. So far, no defense has been demonstrated effective in this scenario. We show for the first time that this attack is detectable using stateful defenses, which store the queries made to the classifier and detect the abnormal cases in which they are similar. Once a malicious query is detected, the account of the user who made it can be blocked. Thus, the attacker must create many accounts to perpetrate the attack. To decrease this number, the attacker could create the adversarial program against a surrogate classifier and then fine-tune it by making few queries to the target model. In this scenario, the effectiveness of the stateful defense is reduced, but we show that it is still effective.

One of the most common causes of lack of continuity of online systems stems from a widely popular Cyber Attack known as Distributed Denial of Service (DDoS), in which a network of infected devices (botnet) gets exploited to flood the computational capacity of services through the commands of an attacker. This attack is made by leveraging the Domain Name System (DNS) technology through Domain Generation Algorithms (DGAs), a stealthy connection strategy that yet leaves suspicious data patterns. To detect such threats, advances in their analysis have been made. For the majority, they found Machine Learning (ML) as a solution, which can be highly effective in analyzing and classifying massive amounts of data. Although strongly performing, ML models have a certain degree of obscurity in their decision-making process. To cope with this problem, a branch of ML known as Explainable ML tries to break down the black-box nature of classifiers and make them interpretable and human-readable. This work addresses the problem of Explainable ML in the context of botnet and DGA detection, which at the best of our knowledge, is the first to concretely break down the decisions of ML classifiers when devised for botnet/DGA detection, therefore providing global and local explanations.

The presence and persistence of Android malware is an on-going threat that plagues this information era, and machine learning technologies are now extensively used to deploy more effective detectors that can block the majority of these malicious programs. However, these algorithms have not been developed to pursue the natural evolution of malware, and their performances significantly degrade over time because of such concept-drift. Currently, state-of-the-art techniques only focus on detecting the presence of such drift, or they address it by relying on frequent updates of models. Hence, there is a lack of knowledge regarding the cause of the concept drift, and ad-hoc solutions that can counter the passing of time are still under-investigated. In this work, we commence to address these issues as we propose (i) a drift-analysis framework to identify which characteristics of data are causing the drift, and (ii) SVM-CB, a time-aware classifier that leverages the drift-analysis information to slow down the performance drop. We highlight the efficacy of our contribution by comparing its degradation over time with a state-of-the-art classifier, and we show that SVM-CB better withstands the distribution changes that naturally characterize the malware domain. We conclude by discussing the limitations of our approach and how our contribution can be taken as a first step towards more time-resistant classifiers that not only tackle, but also understand the concept drift that affects data.

While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable security evaluations of machine learning using practical attacks, reporting a use case on Windows malware detection.

Despite the large body of academic work on machine learning security, little is known about the occurrence of attacks on machine learning systems in the wild. In this paper, we report on a quantitative study with 139 industrial practitioners. We analyze attack occurrence and concern and evaluate statistical hypotheses on factors influencing threat perception and exposure. Our results shed light on real-world attacks on deployed machine learning. On the organizational level, while we find no predictors for threat exposure in our sample, the amount of implement defenses depends on exposure to threats or expected likelihood to become a target. We also provide a detailed analysis of practitioners' replies on the relevance of individual machine learning attacks, unveiling complex concerns like unreliable decision making, business information leakage, and bias introduction into models. Finally, we find that on the individual level, prior knowledge about machine learning security influences threat perception. Our work paves the way for more research about adversarial machine learning in practice, but yields also insights for regulation and auditing., Comment: Accepted at TIFS, version with more detailed appendix containing more detailed statistical results. 17 pages, 6 tables and 4 figures

Machine learning algorithms are increasingly being applied in security-related tasks such as spam and malware detection, although their security properties against deliberate attacks have not yet been widely understood. Intelligent and adaptive attackers may indeed exploit specific vulnerabilities exposed by machine learning techniques to violate system security. Being robust to adversarial data manipulation is thus an important, additional requirement for machine learning algorithms to successfully operate in adversarial settings. In this work, we evaluate the security of Support Vector Machines (SVMs) to well-crafted, adversarial label noise attacks. In particular, we consider an attacker that aims to maximize the SVM's classification error by flipping a number of labels in the training data. We formalize a corresponding optimal attack strategy, and solve it by means of heuristic approaches to keep the computational complexity tractable. We report an extensive experimental analysis on the effectiveness of the considered attacks against linear and non-linear SVMs, both on synthetic and real-world datasets. We finally argue that our approach can also provide useful insights for developing more secure SVM learning algorithms, and also novel techniques in a number of related research areas, such as semi-supervised and active learning.

Adversarial attacks against deep learning-based object detectors have been studied extensively in the past few years. Most of the attacks proposed have targeted the model's integrity (i.e., caused the model to make incorrect predictions), while adversarial attacks targeting the model's availability, a critical aspect in safety-critical domains such as autonomous driving, have not yet been explored by the machine learning research community. In this paper, we propose a novel attack that negatively affects the decision latency of an end-to-end object detection pipeline. We craft a universal adversarial perturbation (UAP) that targets a widely used technique integrated in many object detector pipelines -- non-maximum suppression (NMS). Our experiments demonstrate the proposed UAP's ability to increase the processing time of individual frames by adding "phantom" objects that overload the NMS algorithm while preserving the detection of the original objects which allows the attack to go undetected for a longer period of time.

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative of the data that will be encountered at test time. This assumption is challenged by the threat of poisoning, an attack that manipulates the training data to compromise the model's performance at test time. Although poisoning has been acknowledged as a relevant threat in industry applications, and a variety of different attacks and defenses have been proposed so far, a complete systematization and critical review of the field is still missing. In this survey, we provide a comprehensive systematization of poisoning attacks and defenses in machine learning, reviewing more than 100 papers published in the field in the last 15 years. We start by categorizing the current threat models and attacks, and then organize existing defenses accordingly. While we focus mostly on computer-vision applications, we argue that our systematization also encompasses state-of-the-art attacks and defenses for other data modalities. Finally, we discuss existing resources for research in poisoning, and shed light on the current limitations and open research questions in this research field., Comment: 35 pages, Accepted at ACM Computing Surveys

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised when such data is maliciously manipulated to mislead the learning process. In this article, we first review poisoning attacks that compromise the training data used to learn ML models, including attacks that aim to reduce the overall performance, manipulate the predictions on specific test samples, and even implant backdoors in the model. We then discuss how to mitigate these attacks using basic security principles, or by deploying ML-oriented defensive mechanisms. We conclude our article by formulating some relevant open challenges which are hindering the development of testing methods and benchmarks suitable for assessing and improving the trustworthiness of ML models against data poisoning attacks, Comment: preprint, 10 pages, 3 figures. Paper accepted to the IEEE Computer - Special Issue on Trustworthy AI

Sponge examples are test-time inputs carefully optimized to increase energy consumption and latency of neural networks when deployed on hardware accelerators. In this work, we are the first to demonstrate that sponge examples can also be injected at training time, via an attack that we call sponge poisoning. This attack allows one to increase the energy consumption and latency of machine-learning models indiscriminately on each test-time input. We present a novel formalization for sponge poisoning, overcoming the limitations related to the optimization of test-time sponge examples, and show that this attack is possible even if the attacker only controls a few model updates; for instance, if model training is outsourced to an untrusted third-party or distributed via federated learning. Our extensive experimental analysis shows that sponge poisoning can almost completely vanish the effect of hardware accelerators. We also analyze the activations of poisoned models, identifying which components are more vulnerable to this attack. Finally, we examine the feasibility of countermeasures against sponge poisoning to decrease energy consumption, showing that sanitization methods may be overly expensive for most of the users., Comment: Preprint;16 pages

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning, potentially leading to suboptimal robustness evaluations. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches, optimized to generalize across different models, and readily applicable to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations. We showcase the usefulness of this dataset by testing the effectiveness of the computed patches against 127 models. We conclude by discussing how our dataset could be used as a benchmark for robustness, and how our methodology can be generalized to other domains. We open source our dataset and evaluation code at https://github.com/pralab/ImageNet-Patch.

Adversarial reprogramming allows repurposing a machine-learning model to perform a different task. For example, a model trained to recognize animals can be reprogrammed to recognize digits by embedding an adversarial program in the digit images provided as input. Recent work has shown that adversarial reprogramming may not only be used to abuse machine-learning models provided as a service, but also beneficially, to improve transfer learning when training data is scarce. However, the factors affecting its success are still largely unexplained. In this work, we develop a first-order linear model of adversarial reprogramming to show that its success inherently depends on the size of the average input gradient, which grows when input gradients are more aligned, and when inputs have higher dimensionality. The results of our experimental analysis, involving fourteen distinct reprogramming tasks, show that the above factors are correlated with the success and the failure of adversarial reprogramming.

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.

Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken under more rigorous evaluations. Although guidelines and best practices have been suggested to improve current adversarial robustness evaluations, the lack of automatic testing and debugging tools makes it difficult to apply these recommendations in a systematic manner. In this work, we overcome these limitations by: (i) categorizing attack failures based on how they affect the optimization of gradient-based attacks, while also unveiling two novel failures affecting many popular attack implementations and past evaluations; (ii) proposing six novel indicators of failure, to automatically detect the presence of such failures in the attack optimization process; and (iii) suggesting a systematic protocol to apply the corresponding fixes. Our extensive experimental analysis, involving more than 15 models in 3 distinct application domains, shows that our indicators of failure can be used to debug and improve current adversarial robustness evaluations, thereby providing a first concrete step towards automatizing and systematizing them. Our open-source code is available at: https://github.com/pralab/IndicatorsOfAttackFailure., Comment: Accepted at NeurIPS 2022

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated in a variety of settings and against different models, the factors affecting their effectiveness are still not well understood. In this work, we provide a unifying framework to study the process of backdoor learning under the lens of incremental learning and influence functions. We show that the effectiveness of backdoor attacks depends on: (i) the complexity of the learning algorithm, controlled by its hyperparameters; (ii) the fraction of backdoor samples injected into the training set; and (iii) the size and visibility of the backdoor trigger. These factors affect how fast a model learns to correlate the presence of the backdoor trigger with the target class. Our analysis unveils the intriguing existence of a region in the hyperparameter space in which the accuracy on clean test samples is still high while backdoor attacks are ineffective, thereby suggesting novel criteria to improve existing defenses., Comment: preprint; 28 pages

Although machine learning is widely used in practice, little is known about practitioners' understanding of potential security challenges. In this work, we close this substantial gap and contribute a qualitative study focusing on developers' mental models of the machine learning pipeline and potentially vulnerable components. Similar studies have helped in other security fields to discover root causes or improve risk communication. Our study reveals two \facets of practitioners' mental models of machine learning security. Firstly, practitioners often confuse machine learning security with threats and defences that are not directly related to machine learning. Secondly, in contrast to most academic research, our participants perceive security of machine learning as not solely related to individual models, but rather in the context of entire workflows that consist of multiple components. Jointly with our additional findings, these two facets provide a foundation to substantiate mental models for machine learning security and have implications for the integration of adversarial machine learning into corporate workflows, \new{decreasing practitioners' reported uncertainty}, and appropriate regulatory frameworks for machine learning security., Comment: accepted at SOUPS 2022

Machine learning has been increasingly used as a first line of defense for Windows malware detection. Recent work has however shown that learning-based malware detectors can be evaded by carefully-perturbed input malware samples, referred to as adversarial EXEmples, thus demanding for tools that can ease and automate the adversarial robustness evaluation of such detectors. To this end, we present secml-malware, the first Python library for computing adversarial attacks on Windows malware detectors. \secmlmalware implements state-of-the-art white-box and black-box attacks on Windows malware classifiers, by leveraging a set of feasible manipulations that can be applied to Windows programs while preserving their functionality. The library can be used to perform the penetration testing and assessment of the adversarial robustness of Windows malware detectors, and it can be easily extended to include novel attack strategies. Our library is available at https://github.com/pralab/secml_malware.

One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test time. Availability poisoning is a particularly worrisome subset of poisoning attacks where the attacker aims to cause a Denial-of-Service (DoS) attack. However, the state-of-the-art algorithms are computationally expensive because they try to solve a complex bi-level optimization problem (the "hammer"). We observed that in particular conditions, namely, where the target model is linear (the "nut"), the usage of computationally costly procedures can be avoided. We propose a counter-intuitive but efficient heuristic that allows contaminating the training set such that the target system's performance is highly compromised. We further suggest a re-parameterization trick to decrease the number of variables to be optimized. Finally, we demonstrate that, under the considered settings, our framework achieves comparable, or even better, performances in terms of the attacker's objective while being significantly more computationally efficient., Comment: 8 pages, 7 figures, Submitted to IJCNN 2021

Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current gradient-based attacks to be carefully tuned, initialized, and possibly executed for many computationally-demanding iterations, even if specialized to a given perturbation model. In this work, we overcome these limitations by proposing a fast minimum-norm (FMN) attack that works with different $\ell_p$-norm perturbation models ($p=0, 1, 2, \infty$), is robust to hyperparameter choices, does not require adversarial starting points, and converges within few lightweight steps. It works by iteratively finding the sample misclassified with maximum confidence within an $\ell_p$-norm constraint of size $\epsilon$, while adapting $\epsilon$ to minimize the distance of the current sample to the decision boundary. Extensive experiments show that FMN significantly outperforms existing attacks in terms of convergence speed and computation time, while reporting comparable or even smaller perturbation sizes., Comment: Accepted at NeurIPS'21

Recently, neural network (NN)-based methods, including autoencoders, have been proposed for the detection of cyber attacks targeting industrial control systems (ICSs). Such detectors are often retrained, using data collected during system operation, to cope with the natural evolution (i.e., concept drift) of the monitored signals. However, by exploiting this mechanism, an attacker can fake the signals provided by corrupted sensors at training time and poison the learning process of the detector such that cyber attacks go undetected at test time. With this research, we are the first to demonstrate such poisoning attacks on ICS cyber attack online NN detectors. We propose two distinct attack algorithms, namely, interpolation- and back-gradient based poisoning, and demonstrate their effectiveness on both synthetic and real-world ICS data. We also discuss and analyze some potential mitigation strategies., Comment: ACM SAC'21. arXiv admin note: substantial text overlap with arXiv:2002.02741

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from legitimate training samples at different layer representations - a behavior normally exhibited by adversarial attacks. Despite technical differences, all aforementioned methods share a common backbone structure that we formalize and highlight in this contribution, as it can help in identifying promising research directions and drawbacks of existing methods. The first main contribution of this work is the review of these detection methods in the form of a unifying framework designed to accommodate both existing defenses and newer ones to come. In terms of drawbacks, the overmentioned defenses require comparing input samples against an oversized number of reference prototypes, possibly at different representation layers, dramatically worsening the test-time efficiency. Besides, such defenses are typically based on ensembling classifiers with heuristic methods, rather than optimizing the whole architecture in an end-to-end manner to better perform detection. As a second main contribution of this work, we introduce FADER, a novel technique for speeding up detection-based methods. FADER overcome the issues above by employing RBF networks as detectors: by fixing the number of required prototypes, the runtime complexity of adversarial examples detectors can be controlled. Our experiments outline up to 73x prototypes reduction compared to analyzed detectors for MNIST dataset and up to 50x for CIFAR10 dataset respectively, without sacrificing classification accuracy on both clean and adversarial data., Comment: Submitted as a Neurocomputing journal paper

Recent work has shown that adversarial Windows malware samples - referred to as adversarial EXEmples in this paper - can bypass machine learning-based detection relying on static code analysis by perturbing relatively few input bytes. To preserve malicious functionality, previous attacks either add bytes to existing non-functional areas of the file, potentially limiting their effectiveness, or require running computationally-demanding validation steps to discard malware variants that do not correctly execute in sandbox environments. In this work, we overcome these limitations by developing a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks based on practical, functionality-preserving manipulations to the Windows Portable Executable (PE) file format. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section. Our experimental results show that these attacks outperform existing ones in both white-box and black-box scenarios, achieving a better trade-off in terms of evasion rate and size of the injected payload, while also enabling evasion of models that have been shown to be robust to previous attacks. To facilitate reproducibility of our findings, we open source our framework and all the corresponding attack implementations as part of the secml-malware Python library. We conclude this work by discussing the limitations of current machine learning-based malware detectors, along with potential mitigation strategies based on embedding domain knowledge coming from subject-matter experts directly into the learning process.

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by injecting poisoning samples containing the trigger into the training set, along with the desired class label. Despite the increasing number of studies on backdoor attacks and defenses, the underlying factors affecting the success of backdoor attacks, along with their impact on the learning algorithm, are not yet well understood. In this work, we aim to shed light on this issue by unveiling that backdoor attacks induce a smoother decision function around the triggered samples -- a phenomenon which we refer to as \textit{backdoor smoothing}. To quantify backdoor smoothing, we define a measure that evaluates the uncertainty associated to the predictions of a classifier around the input samples. Our experiments show that smoothness increases when the trigger is added to the input samples, and that this phenomenon is more pronounced for more successful attacks. We also provide preliminary evidence that backdoor triggers are not the only smoothing-inducing patterns, but that also other artificial patterns can be detected by our approach, paving the way towards understanding the limitations of current defenses and designing novel ones., Comment: 9 pages, 7 figures, under submission

Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems. In this paper, we shift the attention to multi-label classification, where the availability of domain knowledge on the relationships among the considered classes may offer a natural way to spot incoherent predictions, i.e., predictions associated to adversarial examples lying outside of the training data distribution. We explore this intuition in a framework in which first-order logic knowledge is converted into constraints and injected into a semi-supervised learning problem. Within this setting, the constrained classifier learns to fulfill the domain knowledge over the marginal distribution, and can naturally reject samples with incoherent predictions. Even though our method does not exploit any knowledge of attacks during training, our experimental analysis surprisingly unveils that domain-knowledge constraints can help detect adversarial examples effectively, especially if such constraints are not known to the attacker., Comment: Accepted for publications in IEEE TPAMI journal

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to evade detection by manipulating data at test time has not yet been thoroughly assessed. While previous work has been mainly focused on devising adversary-aware classification algorithms to counter evasion attempts, only few authors have considered the impact of using reduced feature sets on classifier security against the same attacks. An interesting, preliminary result is that classifier security to evasion may be even worsened by the application of feature selection. In this paper, we provide a more detailed investigation of this aspect, shedding some light on the security properties of feature selection against evasion attacks. Inspired by previous work on adversary-aware classifiers, we propose a novel adversary-aware feature selection model that can improve classifier security against evasion attacks, by incorporating specific assumptions on the adversary's data manipulation strategy. We focus on an efficient, wrapper-based implementation of our approach, and experimentally validate its soundness on different application examples, including spam and malware detection.

While machine-learning algorithms have demonstrated a strong ability in detecting Android malware, they can be evaded by sparse evasion attacks crafted by injecting a small set of fake components, e.g., permissions and system calls, without compromising intrusive functionality. Previous work has shown that, to improve robustness against such attacks, learning algorithms should avoid overemphasizing few discriminant features, providing instead decisions that rely upon a large subset of components. In this work, we investigate whether gradient-based attribution methods, used to explain classifiers' decisions by identifying the most relevant features, can be used to help identify and select more robust algorithms. To this end, we propose to exploit two different metrics that represent the evenness of explanations, and a new compact security measure called Adversarial Robustness Metric. Our experiments conducted on two different datasets and five classification algorithms for Android malware detection show that a strong connection exists between the uniformity of explanations and adversarial robustness. In particular, we found that popular techniques like Gradient*Input and Integrated Gradients are strongly correlated to security when applied to both linear and nonlinear detectors, while more elementary explanation techniques like the simple Gradient do not provide reliable information about the robustness of such classifiers.

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model accuracy of such poisoning attacks have been widely studied, their potential effects on other model performance metrics remain to be evaluated. In this work, we introduce an optimization framework for poisoning attacks against algorithmic fairness, and develop a gradient-based poisoning attack aimed at introducing classification disparities among different groups in the data. We empirically show that our attack is effective not only in the white-box setting, in which the attacker has full access to the target model, but also in a more challenging black-box scenario in which the attacks are optimized against a substitute model and then transferred to the target model. We believe that our findings pave the way towards the definition of an entirely novel set of adversarial attacks targeting algorithmic fairness in different scenarios, and that investigating such vulnerabilities will help design more robust algorithms and countermeasures in the future.

Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient, as they rely on iteratively applying random transformations to the input malware; and (ii) they may also require executing the adversarial malware in a sandbox at each iteration of the optimization process, to ensure that its intrusive functionality is preserved. In this paper, we overcome these issues by presenting a novel family of black-box attacks that are both query-efficient and functionality-preserving, as they rely on the injection of benign content - which will never be executed - either at the end of the malicious file, or within some newly-created sections. Our attacks are formalized as a constrained minimization problem which also enables optimizing the trade-off between the probability of evading detection and the size of the injected payload. We empirically investigate this trade-off on two popular static Windows malware detectors, and show that our black-box attacks can bypass them with only few queries and small payloads, even when they only return the predicted labels. We also evaluate whether our attacks transfer to other commercial antivirus solutions, and surprisingly find that they can evade, on average, more than 12 commercial antivirus engines. We conclude by discussing the limitations of our approach, and its possible future extensions to target malware classifiers based on dynamic analysis.