Picture for Erfan Shayegani

Erfan Shayegani

Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models

Add code
Nov 06, 2024
Viaarxiv icon

Cross-Modal Safety Alignment: Is textual unlearning all you need?

Add code
May 27, 2024
Figure 1 for Cross-Modal Safety Alignment: Is textual unlearning all you need?
Figure 2 for Cross-Modal Safety Alignment: Is textual unlearning all you need?
Figure 3 for Cross-Modal Safety Alignment: Is textual unlearning all you need?
Figure 4 for Cross-Modal Safety Alignment: Is textual unlearning all you need?
Viaarxiv icon

Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Add code
Oct 16, 2023
Viaarxiv icon

Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models

Add code
Jul 26, 2023
Figure 1 for Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models
Figure 2 for Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models
Figure 3 for Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models
Figure 4 for Plug and Pray: Exploiting off-the-shelf components of Multi-Modal Models
Viaarxiv icon