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

CBAT: A Comparative Binary Analysis Tool

Chloe Fortuna (STR), Chris Casinghino (Jane Street), Sam Lasser (Draper), JT Paasch (STR), Cody Roux (AWS), Philip Zucker (Draper)

Read More

EM Eye: Characterizing Electromagnetic Side-channel Eavesdropping on Embedded Cameras

Yan Long (University of Michigan), Qinhong Jiang (Zhejiang University), Chen Yan (Zhejiang University), Tobias Alam (University of Michigan), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejiang University), Kevin Fu (Northeastern University)

Read More

K-LEAK: Towards Automating the Generation of Multi-Step Infoleak Exploits...

Zhengchuan Liang (UC Riverside), Xiaochen Zou (UC Riverside), Chengyu Song (UC Riverside), Zhiyun Qian (UC Riverside)

Read More

MOCK: Optimizing Kernel Fuzzing Mutation with Context-aware Dependency

Jiacheng Xu (Zhejiang University), Xuhong Zhang (Zhejiang University), Shouling Ji (Zhejiang University), Yuan Tian (UCLA), Binbin Zhao (Georgia Institute of Technology), Qinying Wang (Zhejiang University), Peng Cheng (Zhejiang University), Jiming Chen (Zhejiang University)

Read More