41 citations · 45 across the 3 of their papers we have counts for
3 papers
cs.CR2024
On Evaluating the Durability of Safeguards for Open-Weight LLMs
Xiangyu Qi, Boyi Wei, Nicholas Carlini +7
Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical sa…
cs.CL2023★ 41 cited
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Xiangyu Qi, Yi Zeng, Tinghao Xie +4
Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama mode…
cs.CR2023★ 4 cited
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
Tinghao Xie, Xiangyu Qi, Ping He +3
We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense fal…