Research
Here is a GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking
Publication date not yet evaluated · Added arxiv.org
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
GIFT addresses a real privacy risk in multi-tenant LLM serving where bugs can leak one user's sensitive prompts and data to another, offering defenders a low-overhead isolation mechanism for shared GPU inference infrastructure.
GIFT is a research system that enforces user data isolation in LLM serving via GPU Information Flow Tracking, using per-user encryption-as-isolation and static flow analysis of GPU kernels to prevent cross-user data leakage on shared serving infrastructure. Implemented on vLLM and DistServe, it (and its confidential-computing extension GIFT-CC) enforces isolation with 4-10.7% throughput overhead, motivated by real incidents such as ChatGPT cache bugs that exposed other users' chat histories.