most citedBadEdit: Backdooring large language models by model editing

8 citations · 20 across the 6 of their papers we have counts for

collaborators

6 papers

cs.SE2024

BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks

Yisong Xiao, Aishan Liu, Xinwei Zhang +6

Pre-trained large deep learning models are now serving as the dominant component for downstream middleware users and have revolutionized the learning paradigm, replacing the tradit…

cs.AI2024

Compromising Embodied Agents with Contextual Backdoor Attacks

Aishan Liu, Yuguang Zhou, Xianglong Liu +9

Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal…

cs.CR20248 cited

BadEdit: Backdooring large language models by model editing

Yanzhou Li, Tianlin Li, Kangjie Chen +5

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applie…

cs.CL20242 cited

Purifying Large Language Models by Ensembling a Small Language Model

Tianlin Li, Qian Liu, Tianyu Pang +4

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to d…

cs.CL20243 cited

Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One

Tianlin Li, Xiaoyu Zhang, Chao Du +5

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring al…

cs.CV20237 cited

On the Robustness of Segment Anything

Yihao Huang, Yue Cao, Tianlin Li +5

Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt…