ACM Conference on Computer and Communications Security (CCS) BadTV: Unveiling Backdoor Threats in Third-Party Task Vectors
Usenix Security Symposium (USENIX-Security) Unveiling the Pitfalls of Data-Free Backdoor Detection Against Pre-Trained Models
European Conference on Computer Vision (ECCV) GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents
Annual Meeting of the Association for Computational Linguistics (ACL) PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality
Annual Meeting of the Association for Computational Linguistics (ACL) Peering Behind the Shield: Guardrail Identification in Large Language Models