4 papers
Here is a GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking
Jiacheng Shi, Xunjie Wang, Cheng Tan +1
LLM serving frameworks process large volumes of user data--often containing sensitive information--on shared infrastructure. Ensuring isolation between users who share the same ser…
Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B
Shuyi Lin, Tian Lu, Zikai Wang +3
OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought (CoT) reasoning and a Harmony prompt format. We summarize an extensive security evaluati…
TrainVerify: Equivalence-Based Verification for Distributed LLM Training
Yunchi Lu, Youshan Miao, Cheng Tan +4
Training large language models (LLMs) at scale requires parallel execution across thousands of devices, incurring enormous computational costs. Yet, these costly distributed traini…
PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption
Yifan Tan, Cheng Tan, Zeyu Mi +1
Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. None…