41 citations · 67 across the 10 of their papers we have counts for
4 papers · 1 filter
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…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
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…
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks
Xiangyu Qi, Tinghao Xie, Ruizhe Pan +3
One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backd…