Research map / Adversarial robustness and security / Certified and empirical robustness
Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning (Student Abstract)
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add sensitivity triplet loss regularization (MLSA) (ablation) | FGSM baseline · MNIST | AOrig: 99.02 -> 99.38 | Helped |
| Add sensitivity triplet loss regularization (MLSA) (ablation) | FGSM baseline · MNIST | ASA: 98.95 -> 99.17 | Helped |
| Add sensitivity triplet loss regularization (MLSA) (ablation) | FGSM baseline · MNIST | AIA: 85.67 -> 82.49 | Hurt |
| Add invariance triplet loss regularization (MLIA) to sensitivity regularization (ablation) | Baseline + MLSA · MNIST | AIA: 82.49 -> 87.80 | Helped |
| Add invariance triplet loss regularization (MLIA) to sensitivity regularization (ablation) | Baseline + MLSA · MNIST | AOrig: 99.38 -> 99.09 | Hurt |
| Add invariance triplet loss regularization (MLIA) to sensitivity regularization (ablation) | Baseline + MLSA · MNIST | ASA: 99.17 -> 98.98 | Hurt |
| Use angular triplet regularization for both sensitivity and invariance attacks instead of the FGSM baseline | FGSM baseline · MNIST | AIA: 85.67 -> 87.80 | Helped |
| Use angular triplet regularization for both sensitivity and invariance attacks instead of the FGSM baseline | FGSM baseline · MNIST | ASA: 98.95 -> 98.98 | No clear effect |
Closest papers by meaning
- Metric Learning for Adversarial Robustness (NeurIPS 2019 · similarity 0.93)
- Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations (ICML 2020 · similarity 0.89)
- Provably Robust Metric Learning (NeurIPS 2020 · similarity 0.89)
- Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off (ICLR 2025 · similarity 0.89)
- Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing (ICML 2025 · similarity 0.88)
- Enhancing the Adversarial Robustness via Manifold Projection (AAAI 2025 · similarity 0.87)
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.