3 papers
cs.CR2026
Hiding Directions, Leaking Structure: Breaking ArrowCloak through Low-Rank Structure
Beijie Liu, Junyi Ouyang, Haoxuan Xu +4
TEE-shielded inference keeps sensitive state in a trusted execution environment (TEE) while offloading linear algebra to an untrusted accelerator. Wang et al., in Game of Arrows (U…
cs.CR2026
Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference
Chen Gong, Beijie Liu, Mengyuan Li
As large language models (LLMs) grow in scale and are predominantly served from remote platforms, verifying faithful inference execution becomes critical (i.e., ensuring that a pro…
cs.LG2025
Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks
Yuxuan Jiang, Ziming Zhou, Boyu Xu +3
Training deep learning (DL) models is a complex process, making it prone to silent errors that are challenging to detect and diagnose. This paper presents TRAINCHECK, a framework t…