OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services

Documenti analoghi

• S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage
  di: Su, Yue, et al.
  Pubblicazione: (2025)
• Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
  di: Wang, Zhaoqi, et al.
  Pubblicazione: (2025)
• H$_2$O$_2$RAM: A High-Performance Hierarchical Doubly Oblivious RAM
  di: Zheng, Leqian, et al.
  Pubblicazione: (2024)
• CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
  di: Wu, Guanlong, et al.
  Pubblicazione: (2026)
• BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
  di: Li, Hao, et al.
  Pubblicazione: (2025)