Research map / Adversarial robustness and security / Certified and empirical robustness
Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training
Yanyun Wang, Li Liu
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 |
|---|---|---|---|
| add Robust Perception regularizer (RPAT) | Consistency-AT · CIFAR-10 (Linf) | AutoAttack accuracy: 47.72 -> 48.98 | Improved |
| add RPAT | PGD-AT · CIFAR-10 (Linf) | AutoAttack accuracy: 46.74 -> 48.00 | Improved |
| add RPAT | TRADES · CIFAR-10 (Linf) | AutoAttack accuracy: 47.62 -> 47.47 | No clear effect |
| add RPAT | MART · CIFAR-10 (Linf) | clean accuracy: 77.93 -> 75.44 | Hurt |
| add RPAT | PGD-AT · CIFAR-100 (Linf) | AutoAttack accuracy: 25.02 -> 24.88 | No clear effect |
| add RPAT | Consistency-AT · Tiny-ImageNet (Linf) | AutoAttack accuracy: 17.60 -> 18.84 | Improved |
| swap MSE for KL, JS or cosine loss in Robust Perception term (ablation) | PGD-AT+RPAT · CIFAR-10 (Linf) | accuracy | No clear effect |
| use second-to-last layer embedding instead of logits as perception proxy (ablation) | PGD-AT+RPAT · CIFAR-10 (Linf) | AutoAttack accuracy: 48.00 -> 47.89 | No clear effect |
| use alpha 0.5 instead of 0.2, 0.8 or Beta-sampled values (ablation) | RPAT · CIFAR-10 (Linf) | accuracy | Improved |
| add RPAT to ReBAT (RPAT++) | ReBAT · CIFAR-10 (Linf, PreActResNet-18) | mean of clean and AA: 66.405 -> 66.815 | Improved |
| use stronger training adversary (epsilon 10/255 after first decay) (ablation) | ReBAT · CIFAR-10 (Linf, PreActResNet-18) | mean of clean and AA: 66.405 -> 64.240 | Hurt |
| add RPAT to Consistency-AT | Consistency-AT · Tiny-ImageNet (Linf) | mean of clean and AA: 32.070 -> 34.290 | Improved |
Closest papers by meaning
- Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off (ICLR 2022 · similarity 0.91)
- Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness (ICLR 2023 · similarity 0.90)
- Boundary thickness and robustness in learning models (NeurIPS 2020 · similarity 0.89)
- Theoretically Principled Trade-off between Robustness and Accuracy (ICML 2019 · similarity 0.89)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.89)
- Learning Better Certified Models from Empirically-Robust Teachers (NeurIPS 2026 · 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.
