Research map / Adversarial robustness and security / Certified and empirical robustness
Adversarial Robustness for Code
Pavol Bielik, Martin Vechev
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 adversarial training | LSTM · Type inference test | robustness: 44.9\,\pm1.3 -> 51.9\,\pm1.3 | Improved |
| Add adversarial training | DeepTyper · Type inference test | robustness: 52.4\,\pm1.2 -> 55.1\,\pm2.6 | Improved |
| Add adversarial training | GCN · Type inference test | robustness: 49.1\,\pm1.1 -> 49.3\,\pm3.1 | No clear effect |
| Add adversarial training | GNT · Type inference test | robustness: 47.4\,\pm1.0 -> 50.0\,\pm0.5 | Improved |
| Add adversarial training | GGNN · Type inference test | robustness: 52.1\,\pm0.4 -> 57.9\,\pm1.5 | Improved |
| Use abstention, adversarial training, and representation refinement instead of adversarial training alone | GNT · Type inference test, target accuracy 0.00 | robustness: 50.0\,\pm0.5 -> 62.3\% | Improved |
| Use abstention, adversarial training, and representation refinement instead of adversarial training alone | GGNN · Type inference test, target accuracy 0.00 | robustness: 57.9\,\pm1.5 -> 67.0\% | Improved |
| Use abstention, adversarial training, and representation refinement instead of adversarial training alone | GGNN · Type inference test, target accuracy 0.00 | accuracy: 86.1\,\pm0.2 -> 87.7\% | Improved |
Closest papers by meaning
- CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models (AAAI 2023 · similarity 0.91)
- On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks (ICLR 2024 · similarity 0.89)
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples (NeurIPS 2022 · similarity 0.89)
- Towards Deep Learning Models Resistant to Adversarial Attacks (ICLR 2018 · similarity 0.89)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.87)
- On the Scalability of Certified Adversarial Robustness with Generated Data (NeurIPS 2024 · 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.
