1 citations · 3 across the 13 of their papers we have counts for
5 papers · 1 filter
ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
Zhiyu Zhu, Jiayu Zhang, Zhibo Jin +2
Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing fr…
PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN
Jiayu Zhang, Zhiyu Zhu, Xinyi Wang +4
Deep neural networks have demonstrated remarkable performance across various domains. However, they are vulnerable to adversarial examples, which can lead to erroneous predictions.…
Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu +3
Adversarial examples are a key method to exploit deep neural networks. Using gradient information, such examples can be generated in an efficient way without altering the victim mo…
Enhancing Model Interpretability with Local Attribution over Global Exploration
Zhiyu Zhu, Zhibo Jin, Jiayu Zhang +1
In the field of artificial intelligence, AI models are frequently described as `black boxes' due to the obscurity of their internal mechanisms. It has ignited research interest on…
Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu +4
In recent times, the swift evolution of adversarial attacks has captured widespread attention, particularly concerning their transferability and other performance attributes. These…