Papers by Pedram Zaree

2 papers
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment (2025.emnlp-main)

Copied to clipboard

Challenge: Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment.
Approach: They propose a method for generating highly effective Jailbreak attacks that selectively strengthen or weaken attention among different parts of the prompt.
Outcome: The proposed attacks amplify the success rate of existing Jailbreak algorithms while lowering generation cost.
Vulnerabilities of Large Language Models to Adversarial Attacks (2024.acl-tutorials)

Copied to clipboard

Challenge: This tutorial focuses on the vulnerabilities of Large Language Models to adversarial attacks . the tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity .
Approach: This tutorial lays the foundation by explaining safety-aligned LLMs and concepts in cybersecurity.
Outcome: The tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations