6 papers
Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack
Yang Yang, Kevin Wang, Yuanhai Luo +4
The rise of LLM-as-a-Service and other confidential cloud workloads demands cryptographic proof that user data is processed in a trusted, untampered environment. Existing solutions…
LegalCiteBench: Evaluating Citation Reliability in Legal Language Models
Sijia Chen, Hang Yin, Shunfan Zhou
Large language models (LLMs) are increasingly integrated into legal drafting and research workflows, where incorrect citations or fabricated precedents can cause serious profession…
PASS: A Provenanced Access Subaccount System for Blockchain Wallets
Jay Yu, Shunfan Zhou, Hang Yin +1
Blockchain wallets conventionally follow an ownership model where possession of a private key grants unilateral control. However, this assumption is brittle for emerging settings s…
Persistent BitTorrent Trackers
François-Xavier Wicht, Zhengwei Tong, Shunfan Zhou +2
Private BitTorrent trackers enforce upload-to-download ratios to prevent free-riding, but suffer from three critical weaknesses: reputation cannot move between trackers, centralize…
Dstack: A Zero Trust Framework for Confidential Containers
Shunfan Zhou, Kevin Wang, Hang Yin
Web3 applications require execution platforms that maintain confidentiality and integrity without relying on centralized trust authorities. While Trusted Execution Environments (TE…
Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study
Jianwei Zhu, Hang Yin, Peng Deng +2
This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the…