More Like this

1. EAGLE: Evasion Attacks Guided by Local Explanations against Android Malware Classification

   https://doi.org/10.1109/TDSC.2023.3324265  

   Shu, Zhan; Yan, Guanhua (October 2023, IEEE Transactions on Dependable and Secure Computing)

   With machine learning techniques widely used to automate Android malware detection, it is important to investigate the robustness of these methods against evasion attacks. A recent work has proposed a novel problem-space attack on Android malware classifiers, where adversarial examples are generated by transforming Android malware samples while satisfying practical constraints. Aimed to address its limitations, we propose a new attack called EAGLE (Evasion Attacks Guided by Local Explanations), whose key idea is to leverage local explanations to guide the search for adversarial examples. We present a generic algorithmic framework for EAGLE attacks, which can be customized with specific feature increase and decrease operations to evade Android malware classifiers trained on different types of count features. We overcome practical challenges in implementing these operations for four different types of Android malware classifiers. Using two Android malware datasets, our results show that EAGLE attacks can be highly effective at finding functionable adversarial examples. We study the attack transferrability of malware variants created by EAGLE attacks across classifiers built with different classification models or trained on different types of count features. Our research further demonstrates that ensemble classifiers trained from multiple types of count features are not immune to EAGLE attacks. We also discuss possible defense mechanisms against EAGLE attacks. 

   more » « less
2. Directed adversarial sampling attacks on phishing detection

   https://doi.org/10.3233/JCS-191411  

   Shirazi, Hossein; Bezawada, Bruhadeshwar; Ray, Indrakshi; Anderson, Chuck (February 2021, Journal of Computer Security)

   null (Ed.)

   Phishing websites trick honest users into believing that they interact with a legitimate website and capture sensitive information, such as user names, passwords, credit card numbers, and other personal information. Machine learning is a promising technique to distinguish between phishing and legitimate websites. However, machine learning approaches are susceptible to adversarial learning attacks where a phishing sample can bypass classifiers. Our experiments on publicly available datasets reveal that the phishing detection mechanisms are vulnerable to adversarial learning attacks. We investigate the robustness of machine learning-based phishing detection in the face of adversarial learning attacks. We propose a practical approach to simulate such attacks by generating adversarial samples through direct feature manipulation. To enhance the sample’s success probability, we describe a clustering approach that guides an attacker to select the best possible phishing samples that can bypass the classifier by appearing as legitimate samples. We define the notion of vulnerability level for each dataset that measures the number of features that can be manipulated and the cost for such manipulation. Further, we clustered phishing samples and showed that some clusters of samples are more likely to exhibit higher vulnerability levels than others. This helps an adversary identify the best candidates of phishing samples to generate adversarial samples at a lower cost. Our finding can be used to refine the dataset and develop better learning models to compensate for the weak samples in the training dataset. 

   more » « less
3. Robust Ranking Explanations

   Chen, Chao; Guo, Chenghua; Ma, Guixiang; Zeng, Ming; Zhang, Xi; Xie, Sihong (July 2023, Workshop on Interpretable Machine Learning in Healthcare at ICML 2023)

   Robust explanations of machine learning models are critical to establish human trust in the models. Due to limited cognition capability, most humans can only interpret the top few salient features. It is critical to make top salient features robust to adversarial attacks, especially those against the more vulnerable gradient-based explanations. Existing defense measures robustness using lp norms, which have weaker protection power. We define explanation thickness for measuring salient features ranking stability, and derive tractable surrogate bounds of the thickness to design the R2ET algorithm to efficiently maximize the thickness and anchor top salient features. Theoretically, we prove a connection between R2ET and adversarial training. Experiments with a wide spectrum of network architectures and data modalities, including brain networks, demonstrate that R2ET attains higher explanation robustness under stealthy attacks while retaining accuracy. 

   more » « less
4. PATCH-FOOL: ARE VISION TRANSFORMERS ALWAYS ROBUST AGAINST ADVERSARIAL PERTURBATIONS?

   Fu, Yonggan; Zhang, Shunyao; Wu, Shang; Wan, Cheng; Lin, Yingyan (April 2022, Tenth International Conference on Learning Representations (ICLR 2022))

   Vision transformers (ViTs) have recently set off a new wave in neural architecture design thanks to their record-breaking performance in various vision tasks. In parallel, to fulfill the goal of deploying ViTs into real-world vision applications, their robustness against potential malicious attacks has gained increasing attention. In particular, recent works show that ViTs are more robust against adversarial attacks as compared with convolutional neural networks (CNNs), and conjecture that this is because ViTs focus more on capturing global interactions among different input/feature patches, leading to their improved robustness to local perturbations imposed by adversarial attacks. In this work, we ask an intriguing question: “Under what kinds of perturbations do ViTs become more vulnerable learners compared to CNNs?” Driven by this question, we first conduct a comprehensive experiment regarding the robustness of both ViTs and CNNs under various existing adversarial attacks to understand the underlying reason favoring their robustness. Based on the drawn insights, we then propose a dedicated attack framework, dubbed Patch-Fool, that fools the self-attention mechanism by attacking its basic component (i.e., a single patch) with a series of attention-aware optimization techniques. Interestingly, our Patch-Fool framework shows for the first time that ViTs are not necessarily more robust than CNNs against adversarial perturbations. In particular, we find that ViTs are more vulnerable learners compared with CNNs against our Patch-Fool attack which is consistent across extensive experiments, and the observations from Sparse/Mild Patch-Fool, two variants of Patch-Fool, indicate an intriguing insight that the perturbation density and strength on each patch seem to be the key factors that influence the robustness ranking between ViTs and CNNs. It can be expected that our Patch-Fool framework will shed light on both future architecture designs and training schemes for robustifying ViTs towards their real-world deployment. Our codes are available at https://github.com/RICE-EIC/Patch-Fool. 

   more » « less
5. Role of Spatial Context in Adversarial Robustness for Object Detection

   Saha, Aniruddha (July 2020, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops)

   The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. However, one can show that an adversary can design adversarial patches which do not overlap with any objects of interest in the scene and exploit con- textual reasoning to fool standard detectors. In this paper, we examine this problem and design category specific adversarial patches which make a widely used object detector like YOLO blind to an attacker chosen object category. We also show that limiting the use of spatial context during object detector training improves robustness to such adversaries. We believe the existence of context based adversarial attacks is concerning since the adversarial patch can affect predictions without being in vicinity of any objects of interest. Hence, defending against such attacks becomes challenging and we urge the research community to give attention to this vulnerability. 

   more » « less