AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation

Shuyu Chang, Haiping Huang, Yanjun Zhang, Yujin Huang, Fu Xiao, Leo Yu Zhang

AAAI 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Detecting poisoned samples · 1 citations (OpenAlex)

Read the paper

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
use STAB instead of AFRAIDOORbackdoor attack · MNP victim Py150 (PLBART)ASR (%): 68.48 -> 76.89Improved
use STAB instead of AFRAIDOORbackdoor attack · CS victim PyT (PLBART)ASR (%): 78.37 -> 83.67Improved
use STAB instead of AFRAIDOORbackdoor attack · MNP victim CSN (CodeT5)ASR (%): 90.13 -> 95.13Improved
use STAB instead of AFRAIDOORbackdoor attack · MNP Py150, KillBadCode defense (CodeT5)detection recall (%): 27.20 -> 23.02Improved
add SAM to surrogate training (ablation)STAB · MNP victim Py150 (PLBART)ASR (%): 72.21 -> 76.89Improved
add SAM to surrogate training (ablation)STAB · MNP victim Py150 (PLBART)ASR-D (%): 63.92 -> 70.17Improved
add SAM to surrogate training (ablation)STAB · MNP victim CSN (PLBART)ASR (%): 91.12 -> 94.55Improved
add Gumbel-Softmax optimization instead of greedy search (ablation)STAB · MNP victim Py150 (PLBART)ASR-D (%): 67.31 -> 70.17Improved
add Gumbel-Softmax optimization instead of greedy search (ablation)STAB · MNP victim PyT (PLBART)ASR-D (%): 71.42 -> 72.01Improved
add Gumbel-Softmax optimization instead of greedy search (ablation)STAB · MNP victims (PLBART)ASR (%): 74.58 -> 76.89 (Py150); 93.85 -> 94.55 (CSN)Mixed
use static Fixed or Grammar triggers under KillBadCodestatic attacks · MNP Py150, KillBadCode defense (CodeT5)ASR-D (%): 0.0 under defenseHurt

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