Research map / Adversarial robustness and security / Certified and empirical robustness
The Limitations of Adversarial Training and the Blind-Spot Attack
Huan Zhang*, Hongge Chen*, Zhao Song, Duane Boning, Inderjit S. Dhillon, Cho-Jui Hsieh
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 |
|---|---|---|---|
| Evaluate adversarially trained models on brightness- and contrast-adjusted MNIST images | Madry-style adversarial training · MNIST brightness- and contrast-adjusted images | robustness | Hurt |
| Test on examples farther from the training-data manifold | Adversarial training · Test set | robustness | Hurt |
Closest papers by meaning
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.89)
- Regional Adversarial Training for Better Robust Generalization (IJCV 2024 · similarity 0.89)
- Deep Defense: Training DNNs with Improved Adversarial Robustness (NeurIPS 2018 · similarity 0.88)
- Enhancing the Adversarial Robustness via Manifold Projection (AAAI 2025 · similarity 0.88)
- Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks (NeurIPS 2020 · similarity 0.88)
- Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search (CVPR 2019 · similarity 0.88)
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.
