Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarial Attack and Defense in Deep Ranking
Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Nanning Zheng, Gang Hua
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 Anti-Collapse Triplet defense instead of EST | deep ranking model adversarial training · MNIST | ERS: 40.5 -> 78.6 | Improved |
| use Anti-Collapse Triplet defense instead of EST | deep ranking model adversarial training · Fashion-MNIST | ERS: 36.4 -> 67.7 | Improved |
| use Anti-Collapse Triplet defense instead of EST | deep ranking model adversarial training · CUB200-2011 | ERS: 5.3 -> 33.9 | Improved |
| use Anti-Collapse Triplet defense instead of EST | deep ranking model adversarial training · CARS196 | ERS: 7.3 -> 38.6 | Improved |
| use Anti-Collapse Triplet defense instead of EST | deep ranking model adversarial training · SOP | ERS: 31.7 -> 50.8 | Improved |
| keep the query unperturbed in the EST triplet (REST) (ablation) | EST defense · MNIST | ERS: 40.5 -> 71.9 | Improved |
| keep the query unperturbed in the EST triplet (REST) (ablation) | EST defense · Fashion-MNIST | ERS: 36.4 -> 56.9 | Improved |
| keep the query unperturbed in the EST triplet (REST) (ablation) | EST defense · CUB200-2011 | ERS: 5.3 -> 26.6 | Improved |
| keep the query unperturbed in the EST triplet (REST) (ablation) | EST defense · CARS196 | ERS: 7.3 -> 26.1 | Improved |
| keep the query unperturbed in the EST triplet (REST) (ablation) | EST defense · SOP | ERS: 31.7 -> 47.2 | Improved |
| add EST adversarial training | vanilla ranking model · MNIST | ERS: 13.3 -> 40.5 | Improved |
| add EST adversarial training | vanilla ranking model · CUB200-2011 | ERS: 3.8 -> 5.3 | No clear effect |
Closest papers by meaning
- Adversarial Ranking Attack and Defense (ECCV 2020 · similarity 0.98)
- Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off (AAAI 2024 · similarity 0.91)
- Practical Relative Order Attack in Deep Ranking (ICCV 2021 · similarity 0.90)
- Benchmarking Adversarial Robustness on Image Classification (CVPR 2020 · similarity 0.89)
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks (ICLR 2024 · similarity 0.87)
- Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian (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.
