3 citations · 5 across the 10 of their papers we have counts for
12 papers
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
Jiali Wei, Ming Fan, Mingkun Zhang +6
MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or bot…
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…
Forecasting Side Effects of Activation Steering
Chong Yong Ong, Alson Wei Jie Sim, Peixin Zhang +1
Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining. While effective, ste…
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
Qinyan Zhou, Peixin Zhang, Jun Sun +2
While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that…
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…
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Yihao Zhang, Kai Wang, Jiangrong Wu +7
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or u…
NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Rooms
Xingyu Xiao, Jiejuan Tong, Jun Sun +4
The rapid digitization of nuclear power plant main control rooms has fundamentally reshaped operator interaction patterns, introducing complex soft-control behaviors and elevated c…
Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
Xiangxiang Chen, Peixin Zhang, Jun Sun +2
Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce previously overlooked security ris…
LLMScan: Causal Scan for LLM Misbehavior Detection
Mengdi Zhang, Kai Kiat Goh, Peixin Zhang +3
Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularl…
Efficient and Universal Watermarking for LLM-Generated Code Detection
Boquan Li, Zirui Fu, Mengdi Zhang +3
Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and…
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
Peixin Zhang, Jun Sun, Mingtian Tan +1
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor…
Towards Certified Probabilistic Robustness with High Accuracy
Ruihan Zhang, Peixin Zhang, Jun Sun
Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have bee…