Mirage: Provable Defense Against LLM KV Cache Timing Side Channels with Topology-Aware Isolation
cs.CR, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/meta-llama/llama3
Terminology
Sources
- BloombergGPT: A Large Language Model for Finance
- Model Compression and Efficient Inference for Large Language Models: A Survey
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems
- InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
- Auditing Prompt Caching in Language Model APIs
- Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
- OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
- What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Qwen Technical Report
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data