20 citations · 179 across the 97 of their papers we have counts for
17 papers · 1 filter
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
Zheyuan Zhan, Can Wang, Jiawei Chen +4
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's d…
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
Zihao Zhu, Siwei Lyu, Adel Bibi +1
A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specif…
PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
Bo Zheng, Kangran Zhao, Xiaoyu Zhang +7
As generative models continue to advance, AI-generated content (AIGC) is becoming increasingly realistic, weakening the artifact cues commonly exploited by existing detectors. Neve…
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…
Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds
JaeHyeong Chang, Chengzhe Sun, Siwei Lyu
We investigate whether AI-generated impulsive sounds can be distinguished from real ones through group delay analysis. Our central finding is that AI-generated impulsive sounds sho…
Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1
Splitting a bidirectional LSTM's contextual representation into a forward-only (strictly a function of tokens ) and a backward-only (strictly a function of tokens…