Research map / Adversarial robustness and security / Certified and empirical robustness
Interpreting Attributions and Interactions of Adversarial Attacks
Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, Quanshi Zhang
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 |
|---|---|---|---|
| use adversarial training | ResNet-18 · CUB200-2011 | ratio of components in foreground: 63.8% -> 80.8% | Improved |
| use adversarial training | ResNet-18 · Pascal VOC | ratio of components in foreground: 55.6% -> 90.4% | Improved |
| use adversarial training | ResNet-34 · CUB200-2011 | ratio of components in foreground: 69.0% -> 78.6% | Improved |
| use adversarial training | ResNet-34 · Pascal VOC | ratio of components in foreground: 66.2% -> 85.7% | Improved |
| use adversarial training | ResNet-50 · CUB200-2011 | ratio of components in foreground: 62.6% -> 84.9% | Improved |
| use adversarial training | ResNet-50 · Pascal VOC | ratio of components in foreground: 60.8% -> 89.2% | Improved |
| use adversarial training | ResNet-18 · CUB200-2011 | ratio of components decreasing true-class score: 62.8% -> 77.9% | Improved |
| use adversarial training | ResNet-18 · Pascal VOC | ratio of components decreasing true-class score: 34.9% -> 55.3% | Improved |
| use adversarial training | ResNet-34 · CUB200-2011 | ratio of components decreasing true-class score: 44.0% -> 68.4% | Improved |
| use adversarial training | ResNet-34 · Pascal VOC | ratio of components decreasing true-class score: 43.8% -> 63.1% | Improved |
| use adversarial training | ResNet-50 · CUB200-2011 | ratio of components decreasing true-class score: 58.2% -> 82.8% | Improved |
| use adversarial training | ResNet-50 · Pascal VOC | ratio of components decreasing true-class score: 31.6% -> 48.2% | Improved |
Closest papers by meaning
- Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations (CVPR 2020 · similarity 0.89)
- Wide Two-Layer Networks can Learn from Adversarial Perturbations (NeurIPS 2024 · similarity 0.88)
- Theoretical Understanding of Learning from Adversarial Perturbations (ICLR 2024 · similarity 0.88)
- Attack to Explain Deep Representation (CVPR 2020 · similarity 0.88)
- Contrasting Adversarial Perturbations: The Space of Harmless Perturbations (AAAI 2025 · similarity 0.87)
- Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability (ICML 2025 · 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.
