27 citations · 46 across the 25 of their papers we have counts for
25 papers
TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
Bowen Sun, Chaozhuo Li, Yaodong Yang +2
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign q…
ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
Xiaogeng Liu, Xinyan Wang, Yechao Zhang +5
Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time de…
PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Nanxi Li, Zhengyue Zhao, G. Edward Suh +2
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing t…
Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
Yuhao Sun, Jiacheng Zhang, Zesheng Ye +2
Diffusion-based purification (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then rec…
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
Weidi Luo, Shenghong Dai, Xiaogeng Liu +4
The rapid advancements in Large Language Models (LLMs) have enabled their deployment as autonomous agents for handling complex tasks in dynamic environments. These LLMs demonstrate…
VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
Qin Liu, Fei Wang, Chaowei Xiao +1
The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs c…
FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
Jiongxiao Wang, Fangzhou Wu, Wendi Li +5
Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external informa…
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
Yingzi Ma, Jiongxiao Wang, Fei Wang +10
Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy c…
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Qin Liu, Fei Wang, Chaowei Xiao +1
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is unifo…
Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
Qin Liu, Wenjie Mo, Terry Tong +4
The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models sca…
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Xuefeng Du, Chaowei Xiao, Yixuan Li
The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, de…
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Fei Wang, Xingyu Fu, James Y. Huang +18
We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs. MuirBench consists of 12 diverse multi-image tas…
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
Yiquan Li, Zhongzhu Chen, Kun Jin +3
Diffusion Purification, purifying noised images with diffusion models, has been widely used for enhancing certified robustness via randomized smoothing. However, existing framework…
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
Siyuan Ma, Weidi Luo, Yu Wang +1
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), ensuring their safety has become increasingly critical. To achieve this objective, it require…
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…
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors
Jiachen Sun, Changsheng Wang, Jiongxiao Wang +2
Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are h…
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
Yu Wang, Xiaogeng Liu, Yu Li +2
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the i…
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Jiongxiao Wang, Jiazhao Li, Yiquan Li +7
Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. H…
Preference Poisoning Attacks on Reward Model Learning
Junlin Wu, Jiongxiao Wang, Chaowei Xiao +3
Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems,…
Instructional Fingerprinting of Large Language Models
Jiashu Xu, Fei Wang, Mingyu Derek Ma +3
The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication…
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Nan Xu, Fei Wang, Ben Zhou +3
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can pro…
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
Wenjie Mo, Jiashu Xu, Qin Liu +5
Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the c…
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
Jiongxiao Wang, Junlin Wu, Muhao Chen +2
Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignmen…
HiCL: Hierarchical Contrastive Learning of Unsupervised Sentence Embeddings
Zhuofeng Wu, Chaowei Xiao, VG Vinod Vydiswaran
In this paper, we propose a hierarchical contrastive learning framework, HiCL, which considers local segment-level and global sequence-level relationships to improve training effic…