1 citations · 3 across the 6 of their papers we have counts for
7 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…
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…
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
Zhiyuan Yan, Yuhao Luo, Siwei Lyu +2
Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly…
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
Baoyuan Wu, Zihao Zhu, Li Liu +3
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans. Some paradigms have be…