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

SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems

Guangke Chen (ShanghaiTech University), Yedi Zhang (National University of Singapore), Fu Song (Institute of Software, Chinese Academy of Sciences; University of Chinese Academy of Sciences)

Read More

A Duty to Forget, a Right to be Assured?...

Hongsheng Hu (CSIRO's Data61), Shuo Wang (CSIRO's Data61), Jiamin Chang (University of New South Wales), Haonan Zhong (University of New South Wales), Ruoxi Sun (CSIRO's Data61), Shuang Hao (University of Texas at Dallas), Haojin Zhu (Shanghai Jiao Tong University), Minhui Xue (CSIRO's Data61)

Read More

A Preliminary Study on Using Large Language Models in...

Kumar Shashwat, Francis Hahn, Xinming Ou, Dmitry Goldgof, Jay Ligatti, Larrence Hall (University of South Florida), S. Raj Rajagoppalan (Resideo), Armin Ziaie Tabari (CipherArmor)

Read More

AutoWatch: Learning Driver Behavior with Graphs for Auto Theft...

Paul Agbaje, Abraham Mookhoek, Afia Anjum, Arkajyoti Mitra (University of Texas at Arlington), Mert D. Pesé (Clemson University), Habeeb Olufowobi (University of Texas at Arlington)

Read More