Weiran Lin (Carnegie Mellon University), Keane Lucas (Carnegie Mellon University), Neo Eyal (Tel Aviv University), Lujo Bauer (Carnegie Mellon University), Michael K. Reiter (Duke University), Mahmood Sharif (Tel Aviv University)

Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true 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 text 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 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 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.

View More Papers

Commercial Vehicle Electronic Logging Device Security: Unmasking the Risk...

Jake Jepson, Rik Chatterjee, Jeremy Daily (Colorado State University)

Read More

UniID: Spoofing Face Authentication System by Universal Identity

Zhihao Wu (Zhejiang University), Yushi Cheng (Zhejiang University), Shibo Zhang (Zhejiang University), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejing University)

Read More

Pisces: Private and Compliable Cryptocurrency Exchange

Ya-Nan Li (The University of Sydney), Tian Qiu (The University of Sydney), Qiang Tang (The University of Sydney)

Read More

Certificate Transparency Revisited: The Public Inspections on Third-party Monitors

Aozhuo Sun (Institute of Information Engineering, Chinese Academy of Sciences), Jingqiang Lin (School of Cyber Science and Technology, University of Science and Technology of China), Wei Wang (Institute of Information Engineering, Chinese Academy of Sciences), Zeyan Liu (The University of Kansas), Bingyu Li (School of Cyber Science and Technology, Beihang University), Shushang Wen (School of…

Read More