The strength of Nesterov’s accelerated gradient in boosting transferability of stealthy adversarial attacks
Chen Lin, Sheng Long
TL;DR
This paper introduces a new method for creating stealthy adversarial attacks that work well in black-box settings without visible changes.
Contribution
The novel framework Diff-AdaNAG combines Nesterov’s Accelerated Gradient with diffusion mechanisms to enhance transferability and stealthiness in adversarial attacks.
Findings
Diff-AdaNAG improves transferability of adversarial attacks without sacrificing stealthiness.
The method outperforms existing approaches in both white-box and black-box attack scenarios.
The diffusion mechanism helps generate imperceptible adversarial examples aligned with natural data.
Abstract
Deep neural networks have been shown to be highly vulnerable to adversarial examples—inputs crafted to mislead models by adding subtle, human-imperceptible perturbations. Transferability and stealthiness are two crucial metrics for evaluating adversarial attacks. However, these goals often conflict: examples with high transferability typically exhibit noticeable adversarial noise, while those with imperceptible perturbations tend to perform poorly in black-box attacks. To tackle this, we propose Diff-AdaNAG, a novel framework that introduces Nesterov’s Accelerated Gradient (NAG) into diffusion-based adversarial example generation. Specifically, the diffusion mechanism guides the generation process toward the natural data distribution, achieving stealthy attacks with imperceptible adversarial examples. Meanwhile, an adaptive step-size strategy is utilized to harness the strong…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23
Figure 24
Figure 25
Figure 26
Figure 27
Figure 28
Figure 29
Figure 30
Figure 31
Figure 32
Figure 33
Figure 34
Figure 35
Figure 36
Figure 37
Figure 38
Figure 39
Figure 40
Figure 41
Figure 42
Figure 43
Figure 44
Figure 45
Figure 46
Figure 47
Figure 48
Figure 49
Figure 50Peer 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 · Ethics and Social Impacts of AI · Generative Adversarial Networks and Image Synthesis