5 papers
Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
Longtian Wang, Zhengyu Zhao, Chenhao Lin +5
Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present. Existing d…
When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models
Chaoshuo Zhang, Yibo Liang, Mengke Tian +7
Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Mu…
Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
Tianle Song, Chenhao Lin, Yang Cao +5
Mobile motion sensors such as accelerometers and gyroscopes are now ubiquitously accessible by third-party apps via standard APIs. While enabling rich functionalities like activity…
D3: Training-Free AI-Generated Video Detection Using Second-Order Features
Chende Zheng, Ruiqi suo, Chenhao Lin +6
The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the disseminatio…
Concept Unlearning by Modeling Key Steps of Diffusion Process
Chaoshuo Zhang, Chenhao Lin, Zhengyu Zhao +3
Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, existing methods struggle with a cr…