Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post-training methods constructs visual contrasts through image retrieval, generation, or editing to improve fine-grained perception. However, these contrasts are not built...
Ben-Lei Cui, Chun-Yang Chai, Yi-Liang Zhang et al.· 0 citations
A trajectory-guided procedure that identifies candidate injection points and inserts reproducible visual payloads into the observation stream is proposed, which is used to construct MMA-SafetyBench, which contains 1,083 adversarial trajectories across web automation, desktop GUI control, mobile navigation, document und...
Yu-Ke Wang, Ben-Lei Cui, Sheng-Yuan Pang et al.· 0 citations
ProtoArena is introduced, a black-box, multi-component, dynamic benchmark with 80 cross-component vulnerability-exploitation environments spanning 11 protocol and application domains and 7 attack categories and success with limited black-box information remains low and varies across domains and attack categories.
Fa-Sheng Miao, Zhao-Yu Hu, Xiang Li et al.· 0 citations
Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language. Yet existing generative models typically output timestamps without explicit interval-level confidence scores to guide candidate selection. We separate candidate...
FraudBench is a multimodal benchmark for detecting AI-generated fraudulent refund evidence and shows that current MLLMs often recognize real-damaged evidence but fail on many fake-damaged subsets, with fake-damage detection rates far below the 50\% baseline on most generator subsets.
Results reveal a systemic vulnerability of frontier VLMs to meta-adaptive jailbreaks to meta-adaptive jailbreaks and motivate defenses against meta-level adversaries.
Ben-Lei Cui, Sheng-Yuan Pang, Yu-Ke Wang et al.· 1 citation
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific information density, content structure, and evidence patterns, causing fixed video-agent designs to incur redundant processing or fail when mismatched...
Ben-Lei Cui, Ruize Wang, Junjie Li et al.· 1 citation
EvoHarmBench is presented, the first dynamic adversarial evaluation framework for content moderation systems that employs an iterative optimization loop that evolves evasion strategies at the semantic-cluster level, while simultaneously optimizing for evasion success and human readability.
Ruijie Jian, Ben-Lei Cui, Ting Ma et al.· 0 citations
As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. How...
Ting Ma, Xiufeng Huang, Benlei Cui et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.