Papers by Zhongxin Wu
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can replicate insecure patterns from training data. |
| Approach: | They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module. |
| Outcome: | Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines. |
RAP-ID: Mechanistic Prompt Injection Detection via Impostor Behavior Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing defenses rely on externally deployed guardrail models or response inspection . current defenses depend on external guardrails or response inspecting . |
| Approach: | They propose a mechanistic, train-free detection framework that operates exclusively on internal state dynamics during the initial forward pass. |
| Outcome: | The proposed framework achieves competitive performance with significant overall improvements compared to heuristic methods. |