Picture for Zhibo Jin

Zhibo Jin

AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems

Add code
Nov 09, 2024
Figure 1 for AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Figure 2 for AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Figure 3 for AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Figure 4 for AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems
Viaarxiv icon

Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing

Add code
Aug 22, 2024
Viaarxiv icon

Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks

Add code
Aug 22, 2024
Viaarxiv icon

Enhancing Model Interpretability with Local Attribution over Global Exploration

Add code
Aug 14, 2024
Viaarxiv icon

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack

Add code
Aug 14, 2024
Viaarxiv icon

DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks

Add code
Jun 09, 2024
Figure 1 for DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks
Figure 2 for DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks
Figure 3 for DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks
Figure 4 for DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks
Viaarxiv icon

Benchmarking Transferable Adversarial Attacks

Add code
Feb 08, 2024
Viaarxiv icon

GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model

Add code
Jan 30, 2024
Viaarxiv icon

MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks

Add code
Dec 21, 2023
Viaarxiv icon

DANAA: Towards transferable attacks with double adversarial neuron attribution

Add code
Oct 22, 2023
Viaarxiv icon