UCR AI Safety Group

university

https://erfanshayegani.github.io/

AI & ML interests

AI Safety

Recent Activity

Erfan-Shayegani authored a paper 7 months ago

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

Erfan-Shayegani authored a paper 9 months ago

Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Erfan-Shayegani authored a paper 9 months ago

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

View all activity

UCR-AI-Safety's activity

Erfan-Shayegani

authored a paper 7 months ago

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

Paper • 2406.02575 • Published May 27, 2024

Erfan-Shayegani

authored 2 papers 9 months ago

Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Paper • 2310.10844 • Published Oct 16, 2023

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Paper • 2307.14539 • Published Jul 26, 2023 • 2