10 papers
MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
Yilian Liu, Xiaojun Jia, Guoshun Nan +6
Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure…
Disentangling Deception and Hallucination Failures in LLMs
Haolang Lu, Hongrui Peng, WeiYe Fu +5
Failures in large language models (LLMs) are often analyzed from a behavioral perspective, where incorrect outputs in factual question answering are commonly associated with missin…
Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
Jing Tang, Kun Wang, Haolang Lu +7
Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures und…
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
Haolang Lu, Minghui Pan, Ripeng Li +6
Long chain-of-thought (CoT) reasoning improves the performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning step…
Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networks
Xinye Cao, Yihan Lin, Guoshun Nan +9
Zero-Touch Networks (ZTNs) represent a transformative paradigm toward fully automated and intelligent network management, providing the scalability and adaptability required for th…
Reallocating Attention Across Layers to Reduce Multimodal Hallucination
Haolang Lu, Bolun Chu, WeiYe Fu +7
Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between percept…
Revisiting Third-Party Library Detection: A Ground Truth Dataset and Its Implications Across Security Tasks
Jintao Gu, Haolang Lu, Guoshun Nan +5
Accurate detection of third-party libraries (TPLs) is fundamental to Android security, supporting vulnerability tracking, malware detection, and supply chain auditing. Despite many…
KGMark: A Diffusion Watermark for Knowledge Graphs
Hongrui Peng, Haolang Lu, Yuanlong Yu +3
Knowledge graphs (KGs) are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-gener…
Advancing Expert Specialization for Better MoE
Hongcan Guo, Haolang Lu, Guoshun Nan +8
Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly use…
Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
Haolang Lu, Yilian Liu, Jingxin Xu +4
The development of Reasoning Large Language Models (RLLMs) has significantly improved multi-step reasoning capabilities, but it has also made hallucination problems more frequent a…