1 citations · 3 across the 13 of their papers we have counts for
5 papers · 1 filter
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
Zhiyu Zhu, Zhibo Jin, Jiayu Zhang +4
The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), whi…
Benchmarking Transferable Adversarial Attacks
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu +1
The robustness of deep learning models against adversarial attacks remains a pivotal concern. This study presents, for the first time, an exhaustive review of the transferability a…
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model
Zhiyu Zhu, Huaming Chen, Xinyi Wang +5
Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data, i.e., images, text, and audio. Accordingly,…
MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks
Zhiyu Zhu, Huaming Chen, Jiayu Zhang +5
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each i…
DANAA: Towards transferable attacks with double adversarial neuron attribution
Zhibo Jin, Zhiyu Zhu, Xinyi Wang +3
While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attack…