More Like this

1. Evading Provenance-Based ML Detectors with Adversarial System Actions

   Mukherjee, Kunal; Wiedemeier, Joshua; Wang, Tianhao; Wei, James; Chen, Feng; Kim, Muhyun; Kantarcioglu, Murat; Jee, Kangkook (August 2023, Proceedings of The 32nd USENIX Security Symposium (USENIX 2023))

   We present PROVNINJA, a framework designed to generate adversarial attacks that aim to elude provenance-based Machine Learning (ML) security detectors. PROVNINJA is designed to identify and craft adversarial attack vectors that statistically mimic and impersonate system programs. Leveraging the benign execution profile of system processes commonly observed across a multitude of hosts and networks, our research proposes an efficient and effective method to probe evasive alternatives and devise stealthy attack vectors that are difficult to distinguish from benign system behaviors. PROVNINJA's suggestions for evasive attacks, originally derived in the feature space, are then translated into system actions, leading to the realization of actual evasive attack sequences in the problem space. When evaluated against State-of-The-Art (SOTA) detector models using two realistic Advanced Persistent Threat (APT) scenarios and a large collection of fileless malware samples, PROVNINJA could generate and realize evasive attack variants, reducing the detection rates by up to 59%. We also assessed PROVNINJA under varying assumptions on adversaries' knowledge and capabilities. While PROVNINJA primarily considers the black-box model, we also explored two contrasting threat models that consider blind and white-box attack scenarios. 

   more » « less
2. Evading provenance-based ML detectors with adversarial system actions

   Mukherjee, Kunal; Wiedemeier, Joshua; Wang, Tianhao; Wei, James; Chen, Feng; Kim, Muhyun; Kantarcioglu, Murat; Jee, Kangkook (August 2023, SEC '23: Proceedings of the 32nd USENIX Conference on Security Symposium)

   We present PROVNINJA, a framework designed to generate adversarial attacks that aim to elude provenance-based Machine Learning (ML) security detectors. PROVNINJA is designed to identify and craft adversarial attack vectors that statistically mimic and impersonate system programs. Leveraging the benign execution profile of system processes commonly observed across a multitude of hosts and networks, our research proposes an efficient and effective method to probe evasive alternatives and devise stealthy attack vectors that are difficult to distinguish from benign system behaviors. PROVNINJA's suggestions for evasive attacks, originally derived in the feature space, are then translated into system actions, leading to the realization of actual evasive attack sequences in the problem space. When evaluated against State-of-The-Art (SOTA) detector models using two realistic Advanced Persistent Threat (APT) scenarios and a large collection of fileless malware samples, PROVNINJA could generate and realize evasive attack variants, reducing the detection rates by up to 59%. We also assessed PROVNINJA under varying assumptions on adversaries' knowledge and capabilities. While PROVNINJA primarily considers the black-box model, we also explored two contrasting threat models that consider blind and whitebox attack scenarios. 

   more » « less
3. The space of adversarial strategies

   Sheatsley, Ryan; Hoak, Blaine; Pauley, Eric; McDaniel, Patrick (August 2023, 32nd USENIX Security Symposium)

   Adversarial examples, inputs designed to induce worst-case behavior in machine learning models, have been extensively studied over the past decade. Yet, our understanding of this phenomenon stems from a rather fragmented pool of knowledge; at present, there are a handful of attacks, each with disparate assumptions in threat models and incomparable definitions of optimality. In this paper, we propose a systematic approach to characterize worst-case (i.e., optimal) adversaries. We first introduce an extensible decomposition of attacks in adversarial machine learning by atomizing attack components into surfaces and travelers. With our decomposition, we enumerate over components to create 576 attacks (568 of which were previously unexplored). Next, we propose the Pareto Ensemble Attack (PEA): a theoretical attack that upper-bounds attack performance. With our new attacks, we measure performance relative to the PEA on: both robust and non-robust models, seven datasets, and three extended ℓp-based threat models incorporating compute costs, formalizing the Space of Adversarial Strategies. From our evaluation we find that attack performance to be highly contextual: the domain, model robustness, and threat model can have a profound influence on attack efficacy. Our investigation suggests that future studies measuring the security of machine learning should: (1) be contextualized to the domain & threat models, and (2) go beyond the handful of known attacks used today. 

   more » « less
4. The Space of Adversarial Strategies

   Sheatsley, Ryan; Hoak, Blaine; Pauley, Eric; McDaniel, ERic (August 2023, 32nd USENIX Security Symposium)

   Adversarial examples, inputs designed to induce worst-case behavior in machine learning models, have been extensively studied over the past decade. Yet, our understanding of this phenomenon stems from a rather fragmented pool of knowledge; at present, there are a handful of attacks, each with disparate assumptions in threat models and incomparable definitions of optimality. In this paper, we propose a systematic approach to characterize worst-case (i.e., optimal) adversaries. We first introduce an extensible decomposition of attacks in adversarial machine learning by atomizing attack components into surfaces and travelers. With our decomposition, we enumerate over components to create 576 attacks (568 of which were previously unexplored). Next, we propose the Pareto Ensemble Attack (PEA): a theoretical attack that upper-bounds attack performance. With our new attacks, we measure performance relative to the PEA on: both robust and non-robust models, seven datasets, and three extended `pbased threat models incorporating compute costs, formalizing the Space of Adversarial Strategies. From our evaluation we find that attack performance to be highly contextual: the domain, model robustness, and threat model can have a profound influence on attack efficacy. Our investigation suggests that future studies measuring the security of machine learning should: (1) be contextualized to the domain & threat models, and (2) go beyond the handful of known attacks used today. 

   more » « less
5. Group-based Robustness: A General Framework for Customized Robustness in the Real World

   https://doi.org/10.14722/ndss.2024.24084  

   Lin, Weiran; Lucas, Keane; Eyal, Neo; Bauer, Lujo; Reiter, Michael K.; Sharif, Mahmood (February 2024, Network and Distributed System Security Symposium)

   Machine-learning models are known to be vulnerable to evasion attacks, which perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model’s ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between machine-learning models’ vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that, with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and that finding evasive samples, using our new attack strategies, saves time by up to 99% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52 times. 

   more » « less