PredCoin: Defense against Query-based Hard-label Attack
Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar, Ang Li, and Cong Liu

TL;DR
PredCoin is a practical defense mechanism against query-based hard-label black-box attacks on deep neural networks, effectively identifying and disrupting attack queries while maintaining model accuracy.
Contribution
It introduces PredCoin, a novel method that poisons gradient estimation steps to defend against QBHL attacks, a previously unaddressed threat.
Findings
Successfully defends against four state-of-the-art QBHL attacks
Maintains high model accuracy during attacks
Robust against defense-aware attack strategies
Abstract
Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new class of query-based hard-label (QBHL) black-box attacks pose a significant threat to real-world applications (e.g., Google Cloud, Tencent API). Till now, there has been no generalizable and practical approach proposed to defend against such attacks. This paper proposes and evaluates PredCoin, a practical and generalizable method for providing robustness against QBHL attacks. PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks. PredCoin successfully identifies gradient estimation queries crafted by an attacker and introduces uncertainty to the output. Extensive experiments show that PredCoin successfully defends against four state-of-the-art QBHL attacks across various…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Security and Verification in Computing · Advanced Malware Detection Techniques
