AI Paper Atlas

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

AAAI 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 128 citations (OpenAlex)

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 changedWhereMeasuredEffect
identifier renaming via M-H sampling instead of genetic word substitutionblack-box attack on LSTM · OJattack success rate: 10.3 -> 71.3Improved
remove language model filter from GA (ablation)GA · OJ LSTMattack success rate: 10.3 -> 8.9No clear effect
adversarial training with 2,000 MHM examplesLSTM · OJaccuracy: 92.9 -> 94.0Improved
adversarial training with 2,000 MHM examplesLSTM · OJMHM attack rate: 71.3 -> 46.4Improved
adversarial training with 2,000 MHM examplesASTNN · OJaccuracy: 98.2 -> 98.1No clear effect
adversarial training with 2,000 MHM examplesASTNN · OJMHM attack rate: 92.1 -> 54.7Improved
increase number of adversarial examples beyond ~2,000 (ablation)LSTM/ASTNN adv training · OJaccuracy vs robustnessMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy