4 citations · 12 across the 36 of their papers we have counts for
10 papers · 1 filter
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
Nay Myat Min, Long H. Pham, Yige Li +1
Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods--designed for vision/text classification tasks…
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Yige Li, Hanxun Huang, Jiaming Zhang +2
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerabilit…
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
Yunhan Zhao, Xiang Zheng, Lin Luo +3
In this paper, we focus on black-box defense for VLMs against jailbreak attacks. Existing black-box defense methods are either unimodal or bimodal. Unimodal methods enhance either…
AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
Jiaming Zhang, Junhong Ye, Xingjun Ma +5
Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that V…
Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
Wei Zhao, Zhe Li, Yige Li +1
Despite significant ongoing efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behav…
Do Influence Functions Work on Large Language Models?
Zhe Li, Wei Zhao, Yige Li +1
Influence functions are important for quantifying the impact of individual training data points on a model's predictions. Although extensive research has been conducted on influenc…
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
Yige Li, Hanxun Huang, Yunhan Zhao +2
Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers…
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
Wei Zhao, Zhe Li, Yige Li +2
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs ar…
End-to-End Anti-Backdoor Learning on Images and Time Series
Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani +2
Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulat…
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Yige Li, Jiabo He, Hanxun Huang +3
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor…