Enhancing Adversarial Transferability With Cost-Efficient Landscape Flattening

Summary

The paper proposes the Cost-efficient LandscapE Flattening (CLEF) attack, which improves targeted adversarial transferability by optimizing perturbations at both local maxima and local minima of the input loss landscape. CLEF reuses gradients from the previous attack step to reach maxima and uses a probabilistic model, pre-trained on dozens of images from other domains, to sample perturbations that reach minima. Experiments report that this flattens the loss landscape of crafted adversarial examples and improves their transferability.

Related items

• 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)
• InfoVIPA: View-Invariant Projector-Based Adversarial AttackSimilar attack · Arxiv (cs.RO + cs.CV security)