Research map / Adversarial robustness and security / Attacks on text and graphs
Unified Adversarial Patch for Cross-Modal Attacks in the Physical World
Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| optimize patch shape with boundary-limited DE instead of using fixed generic shapes (ablation) | unified adversarial patch · LLVIP, YOLOv3 | ASR: 5.23% -> 73.33% | Improved |
| add score-aware iterative fitness (min-based exponential) instead of simple sum (ablation) | unified adversarial patch · LLVIP, YOLOv3 | ASR: 50.83% -> 73.33% | Improved |
| increase number of patches (ablation) | unified adversarial patch · LLVIP | ASR and AP drop | Improved |
| increase lambda from 1 to 2, then to 3 (ablation) | fitness function · LLVIP | ASR | Mixed |
| shift patch by 3 pixels or 5 pixels (ablation) | unified adversarial patch · LLVIP, YOLOv3 | ASR: 73.33% -> 64.17% (3 px), 55.00% (5 px) | Hurt |
| remove 10% of patch area (ablation) | unified adversarial patch · LLVIP, YOLOv3 | ASR: 73.33% -> 60.83% | Hurt |
| increase shooting angle to +-30 degrees in physical world (ablation) | unified adversarial patch · Physical world | ASR: 73.50% -> 46.50% | Hurt |
| apply spatial smoothing defense | unified adversarial patch · LLVIP, YOLOv3 | ASR: 73.33% -> 64.17% | Hurt |
| apply adversarial training defense | unified adversarial patch · LLVIP, YOLOv3 | ASR: 73.33% -> 50.00% | Hurt |
Closest papers by meaning
- Unified Adversarial Patch for Visible-Infrared Cross-Modal Attacks in the Physical World (TPAMI 2023 · similarity 0.98)
- PAD: Patch-Agnostic Defense against Adversarial Patch Attacks (CVPR 2024 · similarity 0.88)
- Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection (NeurIPS 2024 · similarity 0.88)
- Full-Distance Evasion of Pedestrian Detectors in the Physical World (NeurIPS 2024 · similarity 0.86)
- Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature (AAAI 2025 · similarity 0.86)
- DAP: A Dynamic Adversarial Patch for Evading Person Detectors (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
