VIPA: View-Invariant Projector-Based Adversarial Attack

Summary

VIPA is a projector-based adversarial attack that projects optimized patterns onto real-world scenes to make deep image classifiers mispredict. Unlike earlier stealthy methods that model a single static view, it optimizes projections by aggregating simulated attack losses across multiple viewpoints, so the attack holds across views and classifiers. The authors report higher attack success rates than existing methods in targeted and untargeted settings, with minimal perceptual degradation.

Topics

• Adversarial machine learning

Related items

• 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)
• InfoAdversarial robustness of deep learning-based thyroid nodule segmentation in ultrasoundSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoAnchored Rank-Adversarial Fine-Tuning Pretrained Visual Place Recognition ModelsSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoSay the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAsSimilar attack · Arxiv (cs.RO + cs.CV security)