4 papers
The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
Baoyuan Wu, Qingshan Liu, Adel Bibi +2
This position paper argues that the Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents. The AEG is the divergence between what a principa…
DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection
Kangran Zhao, Yupeng Chen, Xiaoyu Zhang +8
The misuse of advanced generative AI models has resulted in the widespread proliferation of falsified data, particularly forged human-centric audiovisual content, which poses subst…
FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units
Jian Wang, Baoyuan Wu, Li Liu +1
The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods. Existing solutions primarily address unimodal…
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…