Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
원문 초록
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimization-based attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining non-certified white-box-secure defenses at ICLR 2018, we find obfuscated gradients are a common occurrence, with 7 of 9 defenses relying on obfuscated gradients. Our new attacks successfully circumvent 6 completely, and 1 partially, in the original threat model each paper considers.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
Neural Fingerprints for Adversarial Attack Detection
A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment
Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
Cloud Adversarial Example Generation for Remote Sensing Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.