Reverse engineering adversarial attacks with fingerprints from adversarial examples

31 January 2023

Papers citing "Reverse engineering adversarial attacks with fingerprints from adversarial examples"

5 / 5 papers shown

Title
SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks Yue Gao Ilia Shumailov Kassem Fawaz AAML 148 0 0 21 Feb 2025
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network Xiao Guo Vishal Asnani Sijia Liu Xiaoming Liu 27 5 0 03 Dec 2023
Can Adversarial Examples Be Parsed to Reveal Victim Model Information? Yuguang Yao Jiancheng Liu Yifan Gong Xiaoming Liu Yanzhi Wang X. Lin Sijia Liu AAML MLAU 29 1 0 13 Mar 2023
Image classifiers can not be made robust to small perturbations Zheng Dai David K Gifford VLM AAML 24 1 0 07 Dec 2021
Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space Camilo Pestana Naveed Akhtar Wei Liu D. Glance Ajmal Saeed Mian AAML 23 10 0 25 Feb 2020