InfoResearchPreprintLLM-specific
Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
- Published
- Record updated
Summary
The paper proposes DP-SPD, a differentially private inference framework for LLM-as-a-Service that hides a user's real query among client-generated dummy queries and randomly shuffles all queries before they reach the server. It reuses transformer key-value caches across the shared prefixes of the queries to improve decoding efficiency. The authors report strong inference-time privacy and near-plaintext utility on classification and generation tasks, evaluated against QIA, EIA and GPT-based attacks.
Related items
- HighCVE-2026-133631: FlowIntel note variable resolution exposes private case dataSimilar attack · NVD/CVE Database
- InfoCombatting adversarial distillationSimilar attack · OpenAI Blog
- MediumWhen Shuffling Fails: Token Recovery from Obfuscated KV CachesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoEight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag StudySimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumAmazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API KeysSimilar attack · The Hacker News