Search

This is the first work that incorporates recent advancements in "explainability" of machine learning (ML) to build a routing obfuscator called ObfusX. We adopt a recent metric---the SHAP value---which explains to what extent each layout feature can reveal each unknown connection for a recent ML-based split manufacturing attack model. The unique benefits of SHAP-based analysis include the ability to identify the best candidates for obfuscation, together with the dominant layout features which make them vulnerable. As a result, ObfusX can achieve better hit rate (97% lower) while perturbing significantly fewer nets when obfuscating using a via perturbation scheme, compared to prior work. When imposing the same wirelength limit using a wire lifting scheme, ObfusX performs significantly better in performance metrics (e.g., 2.4 times more reduction on average in percentage of netlist recovery).

Website Fingerprinting attacks aim to track the visited websites in browsers and infer confidential information about users. Several studies showed that recent advancements in Machine Learning (ML) and Deep Learning (DL) algorithms made it possible to implement website fingerprinting attacks even though various defense techniques are present in the network. Nevertheless, trained models for website detection are not analyzed deeply to identify the leakage sources which are not always visible to both attackers and Cyber Threat Intelligence engineers. This study focuses on explaining ML and DL models in the context of microarchitecture-based website fingerprinting attacks. In the attack model, performance counters and cache occupancy side-channels are implemented on Google Chrome and Tor browsers. After ML and DL models are trained, LIME and saliency map XAI methods are applied to examine the leakage points in the side-channel data. In order to match the leakage samples in the measurements to the network traces, a novel dataset is collected by utilizing Google Chrome and Firefox browser developer tools. Next, the efficiency of explainable methods are analyzed with XAI metrics. Finally, an XAI-based obfuscation defense technique is proposed as a countermeasure against microarchitecture-based website fingerprinting attacks

App repackaging has been raising serious concerns about the health of the Android ecosystem, and repackage-proofing is an important mitigation against threat of such attacks. However, existing app repackage-proofing schemes were only evaluated against trivial adversaries simulated using analyzers for other purposes (e.g., disclosing privacy leakage vulnerabilities), hence were shown effective mainly because their key programming features were not even supported by those toolkits. Furthermore, existing works have also neglected dynamic adversaries capable of manipulating victim apps at runtime, making them vulnerable against such stronger opponents. In this paper, we propose a novel repackage-proofing framework, which deploys distributed detection and response sites into the subject apps native partition to cross-verify all its code files. The detection sites transmit obtained integrity metrics to response sites via secure communication channels built on the subject apps own control flows using a specialized obfuscation technique based on Collatz conjecture, turning the repackage-proofing process into complicated implicit flows that are intrinsically difficult to be resolved due to the conjectures nonlinear dynamical behaviors. We evaluated our framework using sophisticated Android data-flow analyzers. Results showed that our prototype effectively impeded analyses aiming to trace the information flows of its cross-verification.

Android malware poses a serious security threat to ordinary mobile users. However, the obfuscation technology can generate malware variants, which can bypass existing detection methods and significantly reduce detection accuracy. Aiming at the detection of Android malware obfuscation variants, we propose an efficient anti-obfuscation Android malware detection system MGOPDroid. For different obfuscation technologies, MGOPDroid extracts opcode features with different granularities, combines the TFIDF algorithm and the difference index of opcode feature distribution before and after obfuscation to calculates the weight of opcode features. Then we convert the opcode features into the sequences according to the opcode encoding mapping rules and convert the sequences into grayscale images to achieve feature visualization. A deep learning detection model combined with image enhancement, Resnet, and global average pooling layer is designed to detect malware variants. What’s more, MGOPDroid can be deployed on mobile devices, supports real-time monitoring of application installation and update behavior, and automatically detect malware. Experiments show that the malware detection accuracy for unobfucated samples is 96.35%, and is 94.55% for the obfucated malware. And malware family classification accuracy is 95.31%, while after obfuscating, the classification accuracy rate is 89.96%. On mobile devices, the average time to detect a single application is 3.211 s. Compared with the previous advanced methods, MGOPDroid has obvious advantages in anti-obfuscation effect and efficiency.

Detecting anomalous behavior on smartphones is challenging since malware evolution. Other methodologies detect malicious behavior by analyzing static features of the application code or dynamic data samples obtained from hardware or software. Static analysis is prone to code’s obfuscation while dynamic needs that malicious activities to cease to be dormant in the shortest possible time while data samples are collected. Triggering and capturing malicious behavior in data samples in dynamic analysis is challenging since we need to generate an efficient combination of user’s inputs to trigger these malicious activities. We propose a general model which uses a data collector and analyzer to unveil malicious behavior by analyzing the device’s power consumption since this summarizes the changes in software. The data collector uses an automated tool to generate user inputs. The data analyzer uses changepoint analysis to extract features from power consumption and machine learning techniques to train these features. The data analyzer stage contains two methodologies that extract features using parametric and non-parametric changepoint. Our methodologies are efficient in data collection time than a manual method and the data analyzer provides higher accuracy compared to other techniques, reaching over 94% F1-measure for emulated and real malware.

Despite the growing threat posed by Android malware, the research community is still lacking a comprehensive view of common behaviors and emerging trends in malware families active on the platform. Without such view, researchers incur the risk of developing systems that only detect outdated threats, missing the most recent ones. In this paper, we conduct the largest measurement of Android malware behavior to date, analyzing over 1.2 million malware samples that belong to 1.28K families over a period of eight years (from 2010 to 2017). We aim at understanding how Android malware has evolved over time, focusing on repackaging malware. In this type of threat different innocuous apps are piggybacked with a malicious payload (rider), allowing inexpensive malware manufacturing. One of the main challenges posed when studying repackaged malware is slicing the app to split benign components apart from the malicious ones. To address this problem, we use differential analysis to isolate software components that are irrelevant to the campaign and study the behavior of malicious riders alone. Our analysis framework relies on collective repositories and recent advances on the systematization of intelligence extracted from multiple anti-virus vendors. We find that since its infancy in 2010, the Android malware ecosystem has changed significantly, both in the type of malicious activity performed by malware and in the level of obfuscation used to avoid detection. Finally, we discuss what our findings mean for Android malware detection research, highlighting areas that need further attention by the research community. In particular, we show that riders of malware families evolve over time. This evidences important experimental bias in research works levering on automated systems for family identification without considering variants.

Malware obfuscation can make both automatic and manual analysis of its binary code and the contained functionality significantly more time consuming. For malware research it would therefore be useful to be able to study the effects of different obfuscation methods on the resulting binary code. While some obfuscations are applied through rewriting of the binary, others have to be applied at source code level or during compile time. However, the source code of in-the-wild malware is often not available. For this paper, we collected the source code of eleven open source malware samples from the past 12 years and analyzed if they still compile on current systems. Furthermore, basic static analysis was performed to evaluate the usefulness of the resulting binaries for further malware obfuscation research. Our results indicate, that it is possible to compile available samples with moderate effort and the resulting binaries are very well suited for research purposes.

With ever-increasing, internet-connected devices provide an opportunity to fulfil the attacker’s malicious intention. They use malicious programs to compromise the devices and use them to infect others also. The security researchers are straggling to develop a technique that detects all the malware accurately because of the use of invincible techniques in the development of malware such as strong encryption, obfuscation, polymorphic and metamorphic engine. In this context, this paper proposes a novel malware classification with fine-tune convolution neural networks (MCFT-CNN) model. The MCFT-CNN model detects the unknown malware sample without feature engineering and prior knowledge of binary code analysis or reverse engineering, even the advanced evading techniques used to develop the malware. The model uses deep transfer learning to classify the malware images to their respective malware families. The proposed model enhances the ResNet50 model by altering the last layer with a fully connected dense layer. The output of fully connected dense layer and knowledge of ImageNet model are supplied to softmax layer for malware classification. The model is trained with MalImg malware datasets. The proposed model reported 99.18% accuracy and 5.14ms prediction time. The model also shows consistent performance with a relatively larger dataset (Microsoft malware challenge dataset, approximately 500GB) with 98.63% accuracy and 5.15ms prediction time. The proposed model shows consistent efficacy with two benchmark datasets that clarify the model’s generalisability to perform on the diverse datasets.

The system call sequence is widely used as raw data due to its prospective performance in host-based intrusion detection methods using machine learning. However, evolutionary intrusion attacks such as the obfuscation technique can achieve the same invasion purpose and effect while changing the malicious system call combination to bypass the abnormal identification, which makes the detection results not robust and even invalid. In this paper, we present a behavioral semantics enhancement method of system call sequence to overcome the problem. This method combines sequence completion to extend behavior information capacity with system calls abstraction and invocation switching differential encoding to improve abstractive representation ability. To complete behavioral semantics features extraction and data classification, the enhanced sequences are transformed to vector matrices and input into the multi-channel Text-CNN. Evaluation experiments show that the proposed method outperforms all of the compared works significantly, which suggests it has a more accurate and robust performance in detecting obfuscation attacks.

Cyber–Physical systems (CPS) play significant roles in critical infrastructure, smart facility and industrial control system. Lacking adequate security mechanism makes them more vulnerable and fragile than conventional computer systems (Ashibani and Mahmoud, 2017) [1] , which brings about new potential threat to control system. The privacy data of CPS is critical and sensitive in terms of safety and security, of which leakage would facilitate the attacker corrupting manufacturer infrastructures, increasing the risks of human injury and enhancing the potential loss of assets. In particular, we reveal a new threat target to CPS that adversary can remotely and easily steal CPS sensitive data, e.g. control program, without requirement for any authentication. Furthermore, to enhance the privacy of CPS program and mitigate the privacy threat target to CPS, in this paper, we propose a novel CPS code protection approach adapting to various control scenarios. We pioneer CSheild, an automatic code obfuscation tool for CPS privacy protection through concealing the sensitive data of CPS control program. Our technique renames and splits the register variables which are used in CPS control program, modifies program’s control flow and appends heterogeneous confusion code to the program. We present a prototype of CSheild which can automatically generate various mutant programs, and demonstrate the feasibility of our CPS code obfuscation approach in real-world experiments. We also validate Csheild obfuscation effectiveness through volunteers test, Kolmogorov–Smirnov test and Shannon Entropy test. Result shows that our approach works well on CPS device and it is effective in code obfuscation.

Monetary assistance is a common request from social ties and can be both an economic lifeline and a financial burden. This study examines the relational work at the heart of such exchanges, examining when and how attempts at mobilizing informal financial assistance are resisted. Using qualitative data from West African factory workers, we demonstrate that individuals who wish to resist the provision of assistance without causing relational damage employ rhetorical strategies designed to justify or obfuscate their refusal, relying heavily on socially legitimate reason-giving. The findings reveal that subjective calculations of resource availability are central to the mobilization of assistance, resistant givers differentiate between justification and obfuscation of refusals, and earmarks can play a role in protecting resources from social demands. More broadly, these findings suggest ways that a differential ability to resist social capital mobilization may generate inequalities within social groups.

Split manufacturing (SM) and layout camouflaging (LC) are two promising techniques to obscure integrated circuits (ICs) from malicious entities during and after manufacturing. While both techniques enable protecting the intellectual property (IP) of ICs, SM can further mitigate the insertion of hardware Trojans (HTs). In this paper, we strive for the "best of both worlds," that is we seek to combine the individual strengths of SM and LC. By jointly extending SM and LC techniques toward 3D integration, an up-and-coming paradigm based on stacking and interconnecting of multiple chips, we establish a modern approach to hardware security. Toward that end, we develop a security-driven CAD and manufacturing flow for 3D ICs in two variations, one for IP protection and one for HT prevention. Essential concepts of that flow are (i) "3D splitting" of the netlist to protect, (ii) obfuscation of the vertical interconnects (i.e., the wiring between stacked chips), and (iii) for HT prevention, a security-driven synthesis stage. We conduct comprehensive experiments on DRC-clean layouts of multi-million-gate DARPA and OpenCores designs (and others). Strengthened by extensive security analysis for both IP protection and HT prevention, we argue that entering the third dimension is eminent for effective and efficient hardware security., Accepted for IEEE TETC

Logic encryption has emerged to be a potential solution to the problem of Intellectual Property (IP)-Piracy and counterfeiting. However, in the recent past, several attacks have been mounted on existing logic encryption strategies to extract the secret key. SAT attack, the most predominant one among them, exploits the unprotected Design-for-Testability (DfT) infrastructure as a backdoor to launch attacks on sequential circuits. Protecting the DfT infrastructure is of paramount importance to ensure the security of an Integrated Chip (IC). In this paper, we propose a new logic encryption scheme which dynamically obfuscates the scan operation for an unauthorized attempt of scan access. A detailed security analysis on the proposed secure DfT infrastructure demonstrates its ability to thwart SAT attack without compromising the testability of the design. A methodical key-gate placement strategy enables the proposed scheme to eliminate the leakage of key information through weak key-gate locations, offering protection against path sensitization and logic cone based attacks. Unlike other state-of-the-art SAT preventive schemes, our proposed method does not suffer from poor output corruption, which is a fundamental requirement of a logic encryption scheme.

Field programmable gate array (FPGA) bitstreams contain information on the functionality of all hardware intellectual property (IP) cores used in a given design, so if an attacker gains access to the bitstream, they can mount attacks on the IP. Various mechanisms have been proposed to protect IP from reverse engineering and theft. However, there are no examples of IP obfuscation in FPGA bitstreams that also intrinsically enable tamper detection and authentication at no additional hardware cost. In this letter, we propose a mutable architecture-based watermarking scheme called WATERMARCH, a novel technique of authenticated obfuscation utilizing a hash-based message authentication code (HMAC) to cryptographically mesh the obfuscation and watermark with the original design, with no additional overhead beyond the underlying obfuscation method. While collaboration between the IP owner and FPGA vendor is necessary to facilitate parsing of the bitstream, once the bitstream is parsable, the watermark can be extracted to prove authorship of the IP or confirm the presence of malicious IP modification, providing tremendous benefits to both IP owners and end users.

Research has proved that supposedly secure encrypted network traffic is actually threatened by privacy and security violations from many aspects. This is mainly due to flow features leaking evidence about user activity and data content. Currently, adversaries can use statistical traffic analysis to create classifiers for network applications and infer users’ sensitive data. In this article, we propose a system that optimally prevents traffic feature leaks. In our first algorithm, we model the packet length probability distribution of the source app to be protected and that of the target app that the source app will resemble. We define a model that mutates the packet lengths of a source app to those lengths from the target app having similar bin probability. This would confuse a classifier by identifying a mutated source app as the target app. In our second obfuscation algorithm, we present an optimized scheme resulting in a trade-off between privacy and complexity overhead. For this reason, we propose a mathematical model for network obfuscation. We formulate analytically the problem of selecting the target app and the length from the target app to mutate to. Then, we propose an algorithm to solve it dynamically. Extensive evaluation of the proposed models, on real app traffic traces, shows significant obfuscation efficiency with relatively acceptable overhead. We were able to reduce a classification accuracy from 91.1% to 0.22% using the first algorithm, with 11.86% padding overhead. The same classification accuracy was reduced to 1.76% with only 0.73% overhead using the second algorithm.

This paper surveys several of the most important applications of the continuous time finance paradigm in portfolio selection and derivatives pricing. While it recognizes the powerful insights that the paradigm offered to researchers and practitioners, it finds that several methodological approaches that it introduced have themselves hardened into paradigms and become dysfunctional. They have downgraded and neglected significant real-world problems because of their inability to model them, or adopted simplifications that had little relevance to the problems that they were supposed to solve. The paper then offers in all cases an alternative methodology that can reach the desired solution via rigorous economic and mathematical reasoning, by replacing mathematical elegance with numerical estimations and approximations.

This article focuses on thwarting reverse-engineering attacks and intellectual property (IP) theft by leveraging charge-recycling adiabatic circuits. The adiabatic circuit operation has recently received attention for the Internet-of-Things (IoT) applications due to high energy efficiency and enhanced security characteristics. Such applications typically consist of resource-constrained designs and are often deployed in the field, making them particularly vulnerable to malicious attacks. PhaseCamouflage is a circuit obfuscation technique that leverages the inherent phase differences (PDs) in power supply voltage of adiabatic logic gates and exhibits strong resistance against structural/removal attacks. The proposed method relies on inserting camouflaged PDs in the power supply voltage of subsequent logic gates while still producing a functional netlist. PhaseCamouflage is a unique logic obfuscation technique with low overhead, particularly applicable to pervasive computing applications where both efficiency and security are of primary concern.

Potential negative consequences of digital surveillance represent an area of increasing concern due to the rising impact of digital and mobile technologies on daily life. The COVID-19 pandemic increased these concerns as governments worldwide turned to both digital and non-digital surveillance to help in the battle to control the spread of the disease. Due to this, surveillance creep (the use of supposedly limited-scope surveillance for increasingly pervasive purposes) is a growing concern. Concerns over digital surveillance have led to some individuals turning to protective measures, including obfuscation and the chilling effect. Obfuscation involves intentionally providing ambiguous or misleading information to interfere with surveillance activities. The chilling effect is the decision to not engage in some behavior due to concerns about the consequences of that behavior. Often, obfuscation is a general protective measure that guards against surveillance across applications and reflects general concerns about privacy and surveillance. In contrast, the chilling effect is application and concern specific. In this paper, we use a research model that draws on the health beliefs model and protection motivation along with data from a survey of American social media users to investigate antecedents of obfuscation and the chilling effect in the context of social media surveillance related to COVID-19. Results indicate that age, sex, social media experience, social media habit, and the perceived surveillance severity impact obfuscation. These same antecedents affect the chilling effect, as does perceived surveillance vulnerability. Although our research is exploratory, the results of our study hold implications for both research and practice.

Editor’s note: This article introduces formal security proofs in the context of integrated circuits obfuscability. — Rosario Cammarota, Intel Labs — Francesco Regazzoni, University of Amsterdam and Universita della Svizzera Italiana

Training accurate deep learning (DL) models require large amounts of training data, significant work in labeling the data, considerable computing resources, and substantial domain expertise. In short, they are expensive to develop. Hence, protecting these models, which are valuable storehouses of intellectual properties (IP), against model stealing/cloning attacks is of paramount importance. Today’s mobile processors feature Neural Processing Units (NPUs) to accelerate the execution of DL models. DL models executing on NPUs are vulnerable to hyperparameter extraction via side-channel attacks and model parameter theft via bus monitoring attacks. This paper presents a novel solution to defend against DL IP theft in NPUs during model distribution and deployment/execution via lightweight, keyed model obfuscation scheme. Unauthorized use of such models results in inaccurate classification. In addition, we present an ideal end-to-end deep learning trusted system composed of: 1) model distribution via hardware root-of-trust and public-key cryptography infrastructure (PKI) and 2) model execution via low-latency memory encryption. We demonstrate that our proposed obfuscation solution achieves IP protection objectives without requiring specialized training or sacrificing the model’s accuracy. In addition, the proposed obfuscation mechanism preserves the output class distribution while degrading the model’s accuracy for unauthorized parties, covering any evidence of a hacked model.

Despite the efforts of antivirus vendors and researchers to overcome the threat of malware and its growth, malware remains a rampant problem causing significant economic and intellectual property loss. Malware developers evade commercial detection tools by introducing minor code changes and obfuscation, leading to the creation of variants of known malware families. The volume of malware variants being introduced is increasing every day, resulting in the need for new methods to detect and classify malware with high scalability in less time. To this end, we propose a novel technique that exploits community detection properties and social network analysis concepts. The proposed method is based on system call graphs obtained by extracting the system calls found in the execution of the malware files. To study the inherent characteristics of different malware families, we extract features conforming to community and social network properties and use them for classification. A set of 5 models ranging from using only OS-level actions, to the model that includes community-level features and social network features have been presented. The highest performance has been shown to arise when community-level features and social network features were used in combination with malware class-level features. A suite of 9 machine learning algorithms have been used, and the results have been compared. Our evaluation results demonstrate that our combined approach outperforms many previously used methods in malware detection and classification, being able to achieve precision, recall, and accuracy of more than 0.97 using Multilayer Perceptron and k-Nearest Neighbors.

Static malware detection approaches are time-consuming and cannot deal with code obfuscation techniques. Dynamic malware detection approaches, on the other hand, address these two challenges, however, suffer from behavioral ambiguity, such as the system calls obfuscation. In this paper, we introduce Markhor, a dynamic and behavior-based malware detection approach. Markhor uses system call data dependency and system call control dependency sequences to create a weighted list of malicious patterns. The list is then used to determine the malicious processes. Next, the similarity of a file system call sequences to a malicious pattern is extracted based on a fuzzy algorithm and the file nature is determined. The evaluation results reveal the efficiency of Markhor in terms of accuracy (0.982), precision (0.976), and F-measure (0.982).

Amazon’s Ring relies on infrastructural obfuscation to hide their infrastructures through urban camouflage (as doorbells, floodlights, sensors) while simultaneously expanding the carceral state and...

In this article, unlike almost all state-of-the-art obfuscation solutions that focus on functional/logic obfuscation, we introduce a new paradigm, called data flow obfuscation, which exploits the essence of asynchronicity. In data flow obfuscation, by benefiting from the handshaking mechanism of asynchronous circuits, the system’s FFs/latches will operate out of sync. Hence, the adversary has no sufficient knowledge to apply unrolling/BMC. Also, due to the inherited asynchronicity, the exact time of writing/capturing data into/from the scan chain becomes hidden. Hence, the SAT attack cannot be applied even while scan chain access is open. Moreover, our new proposed paradigm creates stateful/oscillating combinational cycles into the design which extensively boosts the difficulty of modeling this technique. We also demonstrate how data flow obfuscation could easily be integrated with any circuit at low overhead while there is no limitation such as compromising test flow.

Obfuscation is used to protect programs from analysis and reverse engineering. There are theoretically effective and resistant obfuscation methods, but most of them are not implemented in practice yet. The main reasons are large overhead for the execution of obfuscated code and the limitation of application only to a specific class of programs. On the other hand, a large number of obfuscation methods have been developed that are applied in practice. The existing approaches to the assessment of such obfuscation methods are based mainly on the static characteristics of programs. Therefore, the comprehensive (taking into account the dynamic characteristics of programs) justification of their effectiveness and resistance is a relevant task. It seems that such a justification can be made using machine learning methods, based on feature vectors that describe both static and dynamic characteristics of programs. In this paper, it is proposed to build such a vector on the basis of characteristics of two compared programs: the original and obfuscated, original and deobfuscated, obfuscated and deobfuscated. In order to obtain the dynamic characteristics of the program, a scheme based on a symbolic execution is constructed and presented in this paper. The choice of the symbolic execution is justified by the fact that such characteristics can describe the difficulty of comprehension of the program in dynamic analysis. The paper proposes two implementations of the scheme: extended and simplified. The extended scheme is closer to the process of analyzing a program by an analyst, since it includes the steps of disassembly and translation into intermediate code, while in the simplified scheme these steps are excluded. In order to identify the characteristics of symbolic execution that are suitable for assessing the effectiveness and resistance of obfuscation based on machine learning methods, experiments with the developed schemes were carried out. Based on the obtained results, a set of suitable characteristics is determined.

A webshell is a malicious backdoor that allows remote access and control to a web server by executing arbitrary commands. The wide use of obfuscation and encryption technologies has greatly increased the difficulty of webshell detection. To this end, we propose a novel webshell detection model leveraging the grammatical features extracted from the PHP code. The key idea is to combine the executable data characteristics of the PHP code with static text features for webshell classification. To verify the proposed model, we construct a cleaned data set of webshell consisting of 2,917 samples from 17 webshell collection projects and conduct extensive experiments. We have designed three sets of controlled experiments, the results of which show that the accuracy of the three algorithms has reached more than 99.40%, the highest reached 99.66%, the recall rate has been increased by at least 1.8%, the most increased by 6.75%, and the F1 value has increased by 2.02% on average. It not only confirms the efficiency of the grammatical features in webshell detection but also shows that our system significantly outperforms several state-of-the-art rivals in terms of detection accuracy and recall rate.

Split manufacturing is a method to secure circuits by creating layers of a circuit separately—one layer is manufactured at a trusted foundry and the other at an untrusted foundry. The complete circuit is unknowable without both pieces, thus the circuit cannot be effectively manipulated by, e.g., inserting a hardware Trojan at manufacture time. A prominent example of this approach is the work “Securing Computer Hardware Using 3D Integrated Circuit (IC) Technology and Split Manufacturing for Obfuscation” [1]. In the work, it is claimed that even if an attacker knows the exact layout of a circuit before division, the technique set forth would prevent the attacker from inserting an efficient (i.e., undetectable) hardware Trojan into the circuit unless they possessed knowledge of the trusted layer. This paper is notable because it gives strong theoretical reasons, as opposed to only providing empirical results, to suggest that the proposed method provides security for circuits. In this work, we examine whether this particular split manufacturing approach is effective in protecting redundant circuits, such as implementations of cryptographic ciphers, from the implantation of hardware Trojans. We show that it is indeed possible to insert a Trojan with a much higher success rate, and smaller footprint, than the example discussed in [1], which implies that, at least for this class of circuits, obfuscation provides significantly less security than the authors’ theoretical analysis would suggest. To demonstrate its general applicability, our analysis is carried out not only on a the same type of circuit used as an example in [1] (an implementation of the Data Encryption Standard (DES)) but also an Advanced Encryption Standard (AES) circuit. For both circuits, we demonstrate vast improvement for attacker success using the metrics used in [1]

To protect their digital assets from malware attacks, most users and companies rely on antivirus (AV) software. AVs’ protection is a full-time task against malware: This is similar to a game where malware, e.g., through obfuscation and polymorphism, denial of service attacks, and malformed packets and parameters, tries to circumvent AV defences or make them crash. However, AVs react by complementing signature-based detection with anomaly or behavioral analysis, and by using OS protection, standard code, and binary protection techniques. Further, malware counter-acts, for instance, by using adversarial inputs to avoid detection, and so on. In this cat-and-mouse game, a winning strategy is trying to anticipate the move of the adversary by looking into one’s own weaknesses, seeing how the adversary can penetrate them, and building up appropriate defences or attacks. In this article, we play the role of malware developers and anticipate two novel moves for the malware side to demonstrate the weakness in the AVs and to improve the defences in AVs’ side. The first one consists in simulating mouse events to control AVs, namely, to send them mouse “clicks” to deactivate their protection. We prove that many AVs can be disabled in this way, and we call this class of attacks Ghost Control . The second one consists in controlling whitelisted applications, such as Notepad, by sending them keyboard events (such as “copy-and-paste”) to perform malicious operations on behalf of the malware. We prove that the anti-ransomware protection feature of AVs can be bypassed if we use Notepad as a “puppet” to rewrite the content of protected files as a ransomware would do. Playing with the words, and recalling the cat-and-mouse game, we call this class of attacks Cut-and-Mouse . We tested these two attacks on 29 AVs, and the results show that 14 AVs are vulnerable to Ghost Control attack while all 29 AV programs tested are found vulnerable to Cut-and-Mouse . Furthermore, we also show some weaknesses in additional protection mechanisms of AVs, such as sandboxing and CAPTCHA verification. We have engaged with the affected AV companies, and we reported the disclosure communication with them and their responses.

In this paper, we propose a novel mechanism to normalise metamorphic and obfuscated malware down at the opcode level and hence create an advanced metamorphic malware de-obfuscation and defence system. We name this system as DRLDO, for deep reinforcement learning based de-obfuscator. With the inclusion of the DRLDO as a sub-component, an existing Intrusion Detection System could be augmented with defensive capabilities against ‘zero-day’ attack from obfuscated and metamorphic variants of existing malware. This gains importance, not only because there exists no system till date that use advance DRL to intelligently and automatically normalise obfuscation down even to the opcode level, but also because the DRLDO system does not mandate any changes to the existing IDS. The DRLDO system does not even mandate the IDS’ classifier to be retrained with any new dataset containing obfuscated samples. Hence DRLDO could be easily retrofitted into any existing IDS deployment. We designed, developed, and conducted experiments on the system to evaluate the same against multiple-simultaneous attacks from obfuscations generated from malware samples from a standardised dataset that contain multiple generations of malware. Experimental results prove that DRLDO was able to successfully make the otherwise undetectable obfuscated variants of the malware detectable by an existing pre-trained malware classifier. The detection probability was raised well above the cut-off mark to 0.6 for the classifier to detect the obfuscated malware unambiguously. Further, the de-obfuscated variants generated by DRLDO achieved a very high correlation (of ≈ 0.99) with the base malware. This observation validates that the DRLDO system is actually learning to de-obfuscate and not exploiting a trivial trick.

Software obfuscation techniques are increasingly being used to prevent attackers from exploiting security flaws and launching successful attacks. With research on software obfuscation techniques rapidly growing, many software obfuscation techniques with varying quality and strength have been proposed in the literature. However, the literature on obfuscation techniques has not yet been coherently collated and reviewed. This research paper aims to present an overview of state-of-the-art software obfuscation techniques, focusing on quality and strength. A systematic analysis and synthesis of literature published between 2010 and April 2021 has been performed to identify the common measures to quantify obfuscation and their measures, the publication venue, and the home country of the researchers. We have identified the obfuscation quality attributes, such as potency, resilience, cost, stealth, and similarity, that are the most widely used metrics to evaluate the quality of obfuscation techniques. In addition, different measures have been used to quantify these qualities, such as complexity (to measure potency), human effort (to measure resilience), efficiency (to estimate cost), and multiclass performance metrics, distance measures, and matching method (to quantify similarity). These measures were then categorized into sub-measures. The literature lacks research in the following two areas: empirical research using a case study strategy, i.e., real-world datasets, and measurements of obfuscation stealth. Researchers did not address stealth as clearly as they addressed potency, cost, and similarity.

An increase in the number of Maritime Intelligent Transport Systems (MITSs) also means an increase in the number of information security risks. Usually, the administration and operation of MITSs are done through web servers that are frequently targeted by hackers. In marine transportation industry, malicious code injection attacks (webshell) has been widely exploited by hackers to take full control of Web servers. Traditional webshell detection methods based on pattern matching that are no longer effective against new types of webshell. This motivates us to investigate the problem of detecting obfuscation or unknown webshells, termed OUW problem. In this work, we propose a pattern-matching-deep-learning hybrid ASP.NET webshell detection method (H-DLPMWD) to address the OUW problem. H-DLPMWD is based on Yara-based pattern matching to clean dataset; modeling ASP.NET code files as an operation code index (OCI) vectors; and applying CNN method to train and predict webshell in OCI vectors. To validate H-DLPMWD, our rigorous experimentation demonstrates that H-DLPMWD achieves an excellent accuracy of 98.49%, F1-score of 99.01%, and a low false positive rate of 1.75%.

Ananth and Sahai proposed the projective arithmetic functional encryption (PAFE) and showed that PAFE derives a single-key selective secure functional encryption with the help of the randomizing polynomials scheme (RP), namely PAFE with RP achieves the indistinguishability obfuscation (iO). Their PAFE considers a secret-key type functional encryption only and a public-key counterpart is not known. We propose the public-key version: pkPAFE, and show that pkPAFE with RP derives a public-key functional encryption which is single-key selective secure. This means that our pkPAFE achieves iO as well as the original PAFE by Ananth and Sahai.

The paper describes methods of protection against reverse engineering of logic circuits of pseudo-random number generators (PRNG) on linear and non-linear feedback shift registers. These methods are based on the use of additional logic elements in the structure of the generator to hide its original functionality. Obfuscation of the generator logic circuit changes its design such that the device works correctly only if the signals at the additional key inputs of the generator take on the correct values. It is shown that even with a small bit capacity of generators, it is possible to provide a huge number of PRNG implementations with different numbers of states and different properties. The concept of a (М + 1)-sequence generator is introduced. The possibility of transforming (M – 1)- and (M – 3)-sequences generators into (M + 1)-sequences generators is demonstrated. The proposed methods can be used to ensure the security of IoT devices.

Personalized prices affect fairness concerns, and firms have incentive to invest in technology that obfuscates prices and mitigates consumers’ fairness concerns.

The paper presents obfuscation methods for logic circuits of pseudorandom number generators (PRNG) on shift registers with linear and nonlinear feedback, which are based on the PRNG additional logic elements for protection against reverse engineering. The encryption of the PRNG logic circuit changes its design in the way that the device works correctly only if the signals at the additional key inputs of the PRNG take correct values. Even with a small bit capacity of PRNG, a huge number of PRNG implementations with a different number of states and different properties can be provided. The concept of (М + 1)-sequence generator is introduced. The possibility of transforming generators of (M – 1)-sequence and (M – 3)-sequence into generators of (M + 1)-sequence is demonstrated.

Recently, Zhang et al. proposed a novel public data integrity verification scheme for the cloud storage using indistinguishability obfuscation ( $iO$ ), and extend it to support batch verification and data dynamic operations ( IEEE Transactions on Information Forensics and Security , vol. 12, no. 3, pp. 676–688, Mar. 2017). However, we find that the scheme has two flaws: (a) the self-checking of the uploaded blocks and tags in Store phase is not reliable, i.e., it is easy to generate invalid block-tag pairs without being detected; (b) the extended scheme for data dynamic operations suffers from a chosen message attack, i.e., if some uploaded blocks match a certain pattern, the cloud storage is able to replace any existing block by a forged one without being detected, which violates the scheme’s security model. Then, we provide solutions to these problems while preserving all the desirable features of the original scheme.

As most malware is infectious, anti-analysis and packing techniques supported by commercial protectors are conventionally applied to hinder analysis. When analyzing to detect and block such protected malware, it is necessary to do so in a virtual environment to prevent infection. In terms of packing, it is necessary to analyze using dynamic binary instrumentation (DBI), a dynamic analysis tool, which is advantageous for unpacking because DBI inserts code at run time and analyzes it dynamically. However, malware terminates on its own when it detects a virtual environment or DBI due to anti-analysis techniques. Therefore, it is necessary to also bypass anti-VM and anti-DBI techniques in order to successfully analyze malware in a virtual environment using DBI. It is very difficult for analysts to bypass anti-VM and anti-DBI techniques that are used in commercial protectors because analysts generally have little information on what methods are used or how to even bypass these techniques. In this paper, we suggest guidelines to aid in easy analysis of malware protected by anti-VM and anti-DBI techniques supported by commercial protectors. We analyzed the techniques used by five of the most common commercial protectors, and herein present how to bypass anti-VM and anti-DBI techniques supported by commercial protectors via a detailed algorithm analysis. We performed a bypass experiment after applying each commercial protector to 1573 executable files containing vulnerabilities provided by the National Institute of Standards and Technology (NIST). To our knowledge, this is the first empirical study to suggest detailed bypassing algorithms for anti-VM and anti-DBI techniques used in commercial protectors.

Sensitive information leakages from applications are a critical issue in the Android ecosystem. Despite the advance of techniques to secure applications such as packing and obfuscation, a lot of applications are still under the threat of repackaging attacks that inject malicious code and re-distribute applications. Also, as we are becoming more dependent on mobile technologies, more sensitive information is used on our mobile devices. Hence, it is of great importance to reduce the risk of such sensitive information leaks. In this paper, we first present a threat model that attempts to leak users’ sensitive information by using the repackaging attack, named ReMaCi attack. By analyzing the top 8,546 applications downloaded from Google Play Store, we show that 50% of them are really vulnerable to the ReMaCi attack. We, thus, propose a novel, automated static anti-analysis tool, called AmpDroid, for preventing sensitive information leaks. AmpDroid identifies sensitive dataflows and isolates the code that handles the sensitive data from an application. To demonstrate the effectiveness of AmpDroid, we perform the security and performance evaluation of AmpDroid, comparing it with other obfuscation tools.

As encrypted traffic grows, network flow classification has become a significant issue because of the impossibility to parse the payload in an encrypted packet. A possible packet sniffing location for organizations is an under control gateway between intranet and internet to inspect network traffic. However, when an intranet user uses an identity obfuscation protocol such as VPN or TOR, the packet IP and port would be rewritten to preserve user privacy. The same user’s packet sniffed between a user and TOR entry node/VPN proxy always has the same 5-tuples (packets with the same source IP, destination IP, source port, destination port, and IP protocol defined as flow). Thus, we cannot rely on the 5-tuples rule to split traffic into flows. This challenge is called the “only one flow problem” and poses an obstacle for flow classification. A previous solution uses timeout value to determine flow separation points to address this issue. However, the predefined static time threshold cannot fit all user habits, which leads to separation errors. To overcome timeout limitations, we propose a flexible method called AI-FlowDet by leveraging the scene change concept and a CNN model to find behavior change points of traffic based on learning data. AI-FlowDet can apply to the traffic of the identity obfuscation protocols. Next, we propose 294 size-based and direction-based features that can be used with AI-FlowDet to evaluate flow type classification performance. Every experiment leverages different machine learning algorithms. The results show that AI-FlowDet with the proposed features can achieve 98.5% weighted accuracy, which is increased by 12.6% versus the previous timeout method with baseline features. We proved that the proposed splitting methods for the only one flow problem and proposed features for flow type classification are effective based on the good results obtained for both the VPN and TOR datasets.

Intellectual property (IP) protection against piracy and reverse engineering (RE) has emerged as a critical area of research in the field of hardware security. Logic locking has been studied as a promising technique to provide robust protection against these attacks. However, a vast body of recent works has presented successful attacks to break existing locking methods in terms of retrieving the secret key and restoring the original functionality. In this paper, we propose SARO, a scalable attack-resistant logic locking that provides a robust functional and structural design transformation process. SARO treats the target circuit as a hypergraph (G), and performs partitioning of G to produce a set of sub-graphs, then applies an efficient Truth Table Transformation (T3) process to each partition. Further, to mitigate specific attacks (such as SAT-based analysis), SARO implements distributed attack resistance , which integrates random SAT-hard functions (obtained from an automatic function generator, RanSAT) into select partitions. RanSAT produces non-biased and non-deterministic design transformations, where added locking mechanisms are not distinguishable from the original circuit. Finally, it implements a concept of a derived key generation that simultaneously helps to minimize the required key size through judicious reuse of key bits, as well as enhancing the structural alterations. Unlike state-of-the-art logic locking solutions, which focus on primarily enhancing robustness against functional query-based attacks, the proposed transformation steps provide the following unique benefits: (1) high scalability to large designs obtained through partitioning; (2) high structural obfuscation leading to resistance to structural attacks; and (3) low key size, while maintaining strong resistance against functional attacks. To quantitatively represent the level of structural and functional transformation, we also propose the $T3_{metric}$ . We evaluate SARO on ISCAS85 and EPFL benchmarks, and provide comprehensive security and performance analysis of our proposed framework.

Obfuscation or Logic locking (LL) is a technique for protecting hardware intellectual property (IP) blocks against diverse threats, including IP theft, reverse engineering, and malicious modifications. State-of-the-art locking techniques primarily focus on securing a design from unauthorized usage by disabling correct functionality – they often do not directly address hiding design intent through structural transformations. They rely on the synthesis tool to introduce structural changes. We observe that this process is insufficient as the resulting changes in circuit topology are: (1) local and (2) predictable. In this paper, we analyze the structural transformations introduced by LL and introduce a potential attack, called SAIL, that can exploit structural artifacts introduced by LL. SAIL uses machine learning (ML) guided structural recovery that exposes a critical vulnerability in these techniques. Through this attack, we demonstrate that the gate-level structure of a locked design can be retrieved in most parts through a systematic set of steps. The proposed attack is applicable to most forms of logic locking, and significantly more powerful than existing attacks, e.g., SAT-based attacks, since it does not require the availability of golden functional responses (e.g., an unlocked IC). Evaluation on benchmark circuits shows that we can recover an average of about 92%, up to 97%, transformations (Top-10 R-Metric) introduced by logic locking. We show that this attack is scalable, flexible, and versatile. Additionally, to evaluate the SAIL attack resilience of a locked design, we present the SIVA-Metric that is fast in terms of computation speed and does not require any training. We also propose possible mitigation steps for incorporating SAIL resilience into a locked design.

In imbalanced network traffic, malicious cyber-attacks can often hide in large amounts of normal data. It exhibits a high degree of stealth and obfuscation in cyberspace, making it difficult for Network Intrusion Detection System(NIDS) to ensure the accuracy and timeliness of detection. This paper researches machine learning and deep learning for intrusion detection in imbalanced network traffic. It proposes a novel Difficult Set Sampling Technique(DSSTE) algorithm to tackle the class imbalance problem. First, use the Edited Nearest Neighbor(ENN) algorithm to divide the imbalanced training set into the difficult set and the easy set. Next, use the KMeans algorithm to compress the majority samples in the difficult set to reduce the majority. Zoom in and out the minority samples' continuous attributes in the difficult set synthesize new samples to increase the minority number. Finally, the easy set, the compressed set of majority in the difficult, and the minority in the difficult set are combined with its augmentation samples to make up a new training set. The algorithm reduces the imbalance of the original training set and provides targeted data augment for the minority class that needs to learn. It enables the classifier to learn the differences in the training stage better and improve classification performance. To verify the proposed method, we conduct experiments on the classic intrusion dataset NSL-KDD and the newer and comprehensive intrusion dataset CSE-CIC-IDS2018. We use classical classification models: random forest(RF), Support Vector Machine(SVM), XGBoost, Long and Short-term Memory(LSTM), AlexNet, Mini-VGGNet. We compare the other 24 methods; the experimental results demonstrate that our proposed DSSTE algorithm outperforms the other methods.

With more than three million applications already in the Android marketplace, various malware detection systems based on machine learning have been proposed to prevent attacks from cybercriminals; most of these systems use static analyses to extract application features. However, many features generated by static analyses can be easily thwarted by obfuscation techniques. Therefore, several researchers have addressed this obfuscation problem with obfuscation-invariant features. However, to the best of our knowledge, no researcher has utilized deobfuscation techniques. To this end, we adopt a code deobfuscation technique with an Android malware detection system and investigate its effects. Experimental results indicate that code deobfuscation can successfully retrieve useful information concealed by obfuscation. Further, we propose interaction terms based on identified feature interactions. The proposed interaction terms aim to eliminate the interference caused by the size of the application and other features because many feature values are correlated to the size of the application. In addition, the experimental results indicate that these interaction terms have a high ranking in terms of feature importance values. Our proposed Android malware detection model achieves 99.55% accuracy and a 94.61% F1-score with the well-known Drebin dataset, which is better than the performance of previous works.

With the rapid development of automation tools including polymorphic and metamorphic engines, generic packers, and genetic programming, many variants of malware have emerged, which pose a significant threat to the Internet security. To effectively detect malware variants, researchers have developed visualization-based approaches that can visualize malware adaptations for in-depth malware analysis. However, most existing visualization approaches rely on the binary image of a malware sample, which fail to provide an effective texture feature representation and thus often result in low efficiency in coping with challenging malware samples. In this paper, we propose SpecView , a malware spectrum visualization framework with singular spectrum transformation. SpecView converts malware binary code into one-dimensional time series spectrum data, and leverages the singular spectrum transformation method to obtain the structural changes preserved in the time series spectrum data. Then, we utilize the particle swarm optimization algorithm to optimize the singular spectrum transformation performance in SpecView. We apply SpecView in the task of malware classification. Extensive experimental results show that SpecView is effective and efficient in malware classification on the Malimg, Malheur, Drebin, and PRAGuard Malgenome Class Encryption datasets, with classification accuracy exceeding 99%, and it can effectively identify malware variants that use evasive techniques such as packer and encryption obfuscation. The proposed method outperforms the state-of-the-art methods on all datasets and the classification accuracy reaches 100% for 5 malware families packed by the UPX packer on the Malimg dataset, as well as 9 malware families that use Class Encryption obfuscation techniques on the PRAGuard Malgenome Class Encryption datasets.

Deep Learning (DL) is a disruptive technology that has changed the landscape of cyber security research. Deep learning models have many advantages over traditional Machine Learning (ML) models, particularly when there is a large amount of data available. Android malware detection or classification qualifies as a big data problem because of the fast booming number of Android malware, the obfuscation of Android malware, and the potential protection of huge values of data assets stored on the Android devices. It seems a natural choice to apply DL on Android malware detection. However, there exist challenges for researchers and practitioners, such as choice of DL architecture, feature extraction and processing, performance evaluation, and even gathering adequate data of high quality. In this survey, we aim to address the challenges by systematically reviewing the latest progress in DL-based Android malware detection and classification. We organize the literature according to the DL architecture, including FCN, CNN, RNN, DBN, AE, and hybrid models. The goal is to reveal the research frontier, with the focus on representing code semantics for Android malware detection. We also discuss the challenges in this emerging field and provide our view of future research opportunities and directions.

Over the last half-century, significant innovations have occurred in the fields of embryology and human assisted reproduction as a result of human embryo research. This dynamic and ethically complex field is generally subject to extensive regulatory oversight. This article examines New Zealand’s legal framework governing such research. It argues that, despite the core legislative objective of establishing a robust and flexible framework, the current legal regime established under the Human Assisted Reproductive Technology Act 2004 is a classic example of regulatory failure. While not a necessary outcome of the devolved, principles-based regulatory scheme, this failure is primarily due to the perceived lack of authority and independence of the statutory policymaking body established under the Act, as well as the broader regulatory environment in which it operates. It argues that a confluence of problems, including Ministerial overreach as well as a lack of transparency and accountability on the part of decision makers, undermine the legitimacy of the current embryo research policy. This regime not only unjustifiably prevents the conduct of valuable embryo research, but also hinders simple quality improvement practices undertaken in the course of ordinary IVF service provision. This article concludes that, given the significance of embryo research as well as the associated ethical and legal challenges, the issue of embryo research should be remitted back to Parliament to legislate directly as a matter of urgency.

Reverse engineering reveals the physical structure as well as the functionality of an intellectual property (IP) and integrated circuit (IC). This opens the door for IP/IC piracy, counterfeiting, and malicious attacks such as Trojan insertions. Camouflaged logic gates that have the same schematic architecture with identical layout is used to operate for different types of Boolean functions to prevent the de-layering of the chip. An enhanced threshold voltage (E-TVD) defined logic family is proposed in this brief that prevents the internal functionality from being revealed. Compared to previous TVD logic family, the total number of transistors and the cascaded transistors from supply to ground is reduced to enhance the overall performance. A 65nm process is used to compare the conventional TVD logic family and the proposed E-TVD logic family. Post layout simulation results show that the proposed E-TVD logic family for a 3-input logic gate is 34% area efficient, 45% faster, and consumes 40% less power compared to conventional TVD design.