5 papers
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.…
Attribution for Enhanced Explanation with Transferable Adversarial eXploration
Zhiyu Zhu, Jiayu Zhang, Zhibo Jin +3
The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. AttEXplore++, an advanced framework bu…
AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Zhiyu Zhu, Zhibo Jin, Hongsheng Hu +5
AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in spe…
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…