Picture for Zhengwei Fang

Zhengwei Fang

Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study

Add code
Jun 11, 2024
Viaarxiv icon

AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization

Add code
May 30, 2024
Figure 1 for AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Figure 2 for AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Figure 3 for AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Figure 4 for AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Viaarxiv icon

How Robust is Google's Bard to Adversarial Image Attacks?

Add code
Sep 21, 2023
Figure 1 for How Robust is Google's Bard to Adversarial Image Attacks?
Figure 2 for How Robust is Google's Bard to Adversarial Image Attacks?
Figure 3 for How Robust is Google's Bard to Adversarial Image Attacks?
Figure 4 for How Robust is Google's Bard to Adversarial Image Attacks?
Viaarxiv icon

Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution

Add code
Sep 24, 2022
Figure 1 for Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution
Figure 2 for Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution
Figure 3 for Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution
Figure 4 for Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution
Viaarxiv icon