1 citations · 2 across the 12 of their papers we have counts for
13 papers
Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons
Wei Zhao, Zhe Li, Peixin Zhang +1
Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this pro…
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
Yige Li, Jun Sun, Wei Zhao +5
Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce…
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Wei Zhao, Zhe Li, Peixin Zhang +1
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect pro…
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Yige Li, Wei Zhao, Zhe Li +6
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional act…
SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security
Wei Zhao, Zhe Li, Jun Sun
Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted prompts bypass safety mechanisms…
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
Yige Li, Zhe Li, Wei Zhao +4
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. Howe…
Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security
Wei Zhao, Zhe Li, Yige Li +1
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs…
Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
Zhe Li, Wei Zhao, Yige Li +1
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, f…
Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
Wei Zhao, Zhe Li, Yige Li +1
Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. How…
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…
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…
Causality Analysis for Evaluating the Security of Large Language Models
Wei Zhao, Zhe Li, Jun Sun
Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts…