2018/12/04 by Horace He, He, Horace, Aaron Lou +9
Computer Science · Mathematics · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Physical Unclonable Functions (PUFs) and Hardware Security #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1812.01198
ICML 2019 Workshop, Security and Privacy of Machine Learning, camera-ready version
openalex publication_date 2018/12/04 · arxiv created 2019/06/21 · arxiv updated 2019/06/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer across models. We hypothesize that adversarial weakness is composed of three sources of bias: architecture, dataset, and random initialization. We show that one can decompose adversarial examples into an architecture-dependent component, data-dependent component, and noise-dependent component and that these components behave intuitively. For example, noise-dependent components transfer poorly to all other models, while architecture-dependent components transfer better to retrained models with the same architecture. In addition, we demonstrate that these components can be recombined to improve transferability without sacrificing efficacy on the original model.