Research map / Adversarial robustness and security / Certified and empirical robustness
Generating Adversarial Examples for Holding Robustness of Source Code Processing Models
Huangzhao Zhang, Zhuo Li, Ge Li, Lei Ma, Yang Liu, Zhi Jin
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 |
|---|---|---|---|
| identifier renaming via M-H sampling instead of genetic word substitution | black-box attack on LSTM · OJ | attack success rate: 10.3 -> 71.3 | Improved |
| remove language model filter from GA (ablation) | GA · OJ LSTM | attack success rate: 10.3 -> 8.9 | No clear effect |
| adversarial training with 2,000 MHM examples | LSTM · OJ | accuracy: 92.9 -> 94.0 | Improved |
| adversarial training with 2,000 MHM examples | LSTM · OJ | MHM attack rate: 71.3 -> 46.4 | Improved |
| adversarial training with 2,000 MHM examples | ASTNN · OJ | accuracy: 98.2 -> 98.1 | No clear effect |
| adversarial training with 2,000 MHM examples | ASTNN · OJ | MHM attack rate: 92.1 -> 54.7 | Improved |
| increase number of adversarial examples beyond ~2,000 (ablation) | LSTM/ASTNN adv training · OJ | accuracy vs robustness | Mixed |
Closest papers by meaning
- Adversarial Robustness for Code (ICML 2020 · similarity 0.88)
- CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models (AAAI 2023 · similarity 0.87)
- AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses (ICML 2025 · similarity 0.83)
- Black-Box Adversarial Attacks on LLM-Based Code Completion (ICML 2025 · similarity 0.83)
- Boosting Adversarial Transferability through Augmentation in Hypothesis Space (CVPR 2025 · similarity 0.82)
- RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection (CVPR 2025 · similarity 0.82)
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.
