4 papers
Geometric Autoencoder for Diffusion Models
Hangyu Liu, Jianyong Wang, Yutao Sun
Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet…
Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach
Hangyu Liu, Bo Peng, Pengxiang Ding +1
Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target clas…
Enhancing Adversarial Transferability via Component-Wise Transformation
Hangyu Liu, Bo Peng, Can Cui +2
Deep Neural Networks (DNNs) are highly vulnerable to adversarial examples, which pose significant challenges in security-sensitive applications. Among various adversarial attack st…
A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
Yuhan Liang, Yijun Li, Yumeng Niu +2
The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and s…