Optimizing stealthiness in universal adversarial perturbations via class-selective and perceptual similarity metrics

Summary

Stealthy-UAP is a framework for generating universal adversarial perturbations that are harder to detect. It combines a Class-Selective Attack, which targets only semantically consistent classes and keeps predictions for non-target inputs unchanged, with Perceptual Similarity Optimization, which uses high-level deep features to align perturbations with the Human Visual System. The authors report that it outperforms state-of-the-art baselines on ImageNet subsets and the full ImageNet validation set, and remains effective under mainstream adversarial defenses.

Topics

• Adversarial machine learning

Related items

• InfoA Layer-wise Study of How Style Rewriting Breaks the Calibration of Zero-Shot LLM Fake-News DetectorsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoEvaluating the robustness of explainable AI methods to adversarial attacks in intrusion and malware detectionSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoRL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement LearningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoEvaluating Parameter-Efficient Fine-Tuning Attacks Against Non-Transferable Learning DefensesSimilar attack · Elsevier Security Journals
• InfoEscalate or Close: How Fast-Tier Models Handle Held-Out Web Attack Families in Two-Tier TriageSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)