Tagged:

2 posts

• Side-Channel Attacks on LLM APIs: What Response Timing and Token Counts Reveal

  How LLM API metadata — token counts, timing, and streaming patterns — leaks system prompt structure and model configuration to adversaries.

  Jul 3, 2026 side-channel llm-security api-security token-inference timing-attacks threat-modeling

• Cross-Tenant Contamination in LLM APIs: When Other Users' Context Leaks Into Your Session

  Multi-tenant LLM deployments — shared inference infrastructure, KV cache reuse, batched requests — create subtle cross-tenant data exposure risks that differ from classical API security vulnerabilities. This post maps the threat surface unique to shared AI inference.

  Jul 2, 2026 prompt-caching timing-attacks kv-cache side-channel llm-security