- [2025/02] I Know What You Asked: Prompt Leakage via KV-Cache Sharing in Multi-Tenant LLM Serving
- [2024/11] InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
- [2024/11] Privacy Risks of Speculative Decoding in Large Language Models
- [2024/09] The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems
- [2024/03] What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
