3 papers
cs.CR2026
ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data
Weizhou Wang, Eric Liu, Xiangyu Guo +3
Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) are trained on vast unlabelled c…
cs.AR2026
ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data Corruptions
Ioanna Vavelidou, Subho S. Banerjee, Eric X. Liu +3
Hyperscaler reports of silent data corruptions (SDCs), presumed to be caused by silicon manufacturing defects, have motivated the development of functional tests for detecting defe…
cs.CL2025
MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
Xiao Hu, Eric Liu, Weizhou Wang +2
Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external so…