Doktorand:in
Annual Meeting of the Association for Computational Linguistics (ACL) Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services
Annual Meeting of the Association for Computational Linguistics (ACL) The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
ACM Conference on Computer and Communications Security (CCS) UnsafeBench: Benchmarking Image Safety Classifiers onReal-World and AI-Generated Images
Usenix Security Symposium (USENIX-Security) From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language
Annual Meeting of the Association for Computational Linguistics (ACL) When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
Annual Meeting of the Association for Computational Linguistics (ACL) JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
IEEE Symposium on Security and Privacy (S&P) GPTracker: A Large-Scale Measurement of Misused GPTs
IEEE Symposium on Security and Privacy (S&P) On the Effectiveness of Prompt Stealing Attacks on In-The-Wild Prompts
Usenix Security Symposium (USENIX-Security)
Usenix Security Symposium (USENIX-Security) HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns