Here is a GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking

arXiv:2608.25431 · cs.CR · Submitted 2026-08-26 · Read on arXiv

cs.CR

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/onnx/onnx

Terminology

• KV cache — 23× in this paper · explained in 3 episodes
• Transformer — 15× in this paper · explained in 2 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Information Flow Tracking — 6× in this paper
• Speculative Decoding — 6× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Communication Overhead — 2× in this paper · explained in 2 episodes
• Differential Privacy — 2× in this paper · explained in 4 episodes
• Symposium on Security and Privacy — 2× in this paper
• AMD Secure Encrypted Virtualization — 1× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Apple Private Cloud Compute — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Formal Methods — 1× in this paper · explained in 3 episodes
• Information Flow Graph — 1× in this paper
• Information Leakage — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Service Level Objectives — 1× in this paper
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation
• LLaMA: Open and Efficient Foundation Language Models
• Characterizing Network Requirements for GPU API Remoting in AI Applications
• SGLang: Efficient Execution of Structured Language Model Programs
• Qwen2.5 Technical Report
• OPT: Open Pre-trained Transformer Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs