2 citations · 5 across the 15 of their papers we have counts for
15 papers
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation
Ruotong Wang, Zihao Zhu, Siwei Lyu +2
Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of seemingly benign components ca…
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Minh Khoi Ho, Zihao Zhu, Runchuan Zhu +4
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making beco…
A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges
Chenchen Kuai, Jiwan Jiang, Zihao Zhu +8
The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and…
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Zihao Zhu, Ruotong Wang, Siwei Lyu +2
The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time,…
Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework
Guanzong Wu, Zihao Zhu, Siwei Lyu +1
Detecting toxicity in multimodal data remains a significant challenge, as harmful meanings often lurk beneath seemingly benign individual modalities: only emerging when modalities…
AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
Zihao Zhu, Xinyu Wu, Gehan Hu +3
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT i…
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
Zihao Zhu, Hongbao Zhang, Ruotong Wang +3
Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers. However, we reveal a critical vulnerabilit…
HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
Zihao Zhu, Hongbao Zhang, Guanzong Wu +2
Visual-textual inconsistency (VTI) evaluation plays a crucial role in cleansing vision-language data. Its main challenges stem from the high variety of image captioning datasets, w…
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
Mingda Zhang, Mingli Zhu, Zihao Zhu +1
Backdoor attack has been considered as a serious security threat to deep neural networks (DNNs). Poisoned sample detection (PSD) that aims at filtering out poisoned samples from an…
EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents
Zihao Zhu, Bingzhe Wu, Zhengyou Zhang +3
Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction. The emergence of foundation models as the "brain" of EAI age…
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
Baoyuan Wu, Hongrui Chen, Mingda Zhang +7
As an emerging approach to explore the vulnerability of deep neural networks (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor…
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
Baoyuan Wu, Hongrui Chen, Mingda Zhang +7
As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdo…
Enhanced Few-Shot Class-Incremental Learning via Ensemble Models
Mingli Zhu, Zihao Zhu, Sihong Chen +2
Few-shot class-incremental learning (FSCIL) aims to continually fit new classes with limited training data, while maintaining the performance of previously learned classes. The mai…
Defenses in Adversarial Machine Learning: A Survey
Baoyuan Wu, Shaokui Wei, Mingli Zhu +7
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsisten…
BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
Meixi Zheng, Xuanchen Yan, Zihao Zhu +2
Adversarial examples are well-known tools to evaluate the vulnerability of deep neural networks (DNNs). Although lots of adversarial attack algorithms have been developed, it's sti…