most citedFine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

41 citations · 49 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL2024

Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability

Haonan Li, Xudong Han, Zenan Zhai +32

To address this gap, we introduce Libra-Leaderboard, a comprehensive framework designed to rank LLMs through a balanced evaluation of performance and safety. Combining a dynamic le…

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.CL2024

Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs

Ashwinee Panda, Berivan Isik, Xiangyu Qi +3

Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive int…

cs.CR20244 cited

Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu +5

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many…

cs.CL202341 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.CR20234 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…