4 papers
In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
Xiao Fang, Yiming Gong, Stanislav Panev +4
Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an ob…
Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection
Feng Ding, Wenhui Yi, Yunpeng Zhou +3
Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward diffe…
Redundant Semantic Environment Filling via Misleading-Learning for Fair Deepfake Detection
Xinan He, Yue Zhou, Shu Hu +3
Detecting falsified faces generated by Deepfake technology is essential for safeguarding trust in digital communication and protecting individuals. However, current detectors often…
Synthesizing Black-box Anti-forensics DeepFakes with High Visual Quality
Bing Fan, Shu Hu, Feng Ding
DeepFake, an AI technology for creating facial forgeries, has garnered global attention. Amid such circumstances, forensics researchers focus on developing defensive algorithms to…