Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition

Summary

This paper presents the first adversarial attack and defense framework for Pedestrian Attribute Recognition (PAR), built on a pre-trained CLIP-based PAR framework. The authors propose ASL-PAR, which generates adversarial noise through global- and patch-level semantic and label perturbations, and a semantic offset defense strategy to suppress such attacks. Experiments on the digital datasets PETA, PA100K, MSP60K and RAPv2, along with physical-domain tests, validate both the attack and the defense.

Related items

• 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)
• InfoDetect, Repair and Audit: A Hierarchical Multi-Agent Defense Against Adversarial Attacks in Energy ForecastingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSANAI: Secure ECC Distributed Keyed Parity Embedded in Weights for Protecting Neural Networks against Bit-Flip AttacksSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoTowards Fine-grained and Robust Detection of Human-AI Co-authorshipSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)