arXiv:2610.32334v1 Announce Type: new Abstract: Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on a trigger. A capable attacker minimizes the number of such samples, since each adds cost and exposure and a lower poisoning rate leaves a smaller footprint for defenses.
Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.32334
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.





