Saved in:
Bibliographic Details
Main Authors: Raheja, Tarun, Pochhi, Nilay, Curie, F. D. C. M.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.09097
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912159556960256
author Raheja, Tarun
Pochhi, Nilay
Curie, F. D. C. M.
author_facet Raheja, Tarun
Pochhi, Nilay
Curie, F. D. C. M.
contents Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, but their vulnerability to jailbreak attacks poses significant security risks. This survey paper presents a comprehensive analysis of recent advancements in attack strategies and defense mechanisms within the field of Large Language Model (LLM) red-teaming. We analyze various attack methods, including gradient-based optimization, reinforcement learning, and prompt engineering approaches. We discuss the implications of these attacks on LLM safety and the need for improved defense mechanisms. This work aims to provide a thorough understanding of the current landscape of red-teaming attacks and defenses on LLMs, enabling the development of more secure and reliable language models.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09097
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations
Raheja, Tarun
Pochhi, Nilay
Curie, F. D. C. M.
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, but their vulnerability to jailbreak attacks poses significant security risks. This survey paper presents a comprehensive analysis of recent advancements in attack strategies and defense mechanisms within the field of Large Language Model (LLM) red-teaming. We analyze various attack methods, including gradient-based optimization, reinforcement learning, and prompt engineering approaches. We discuss the implications of these attacks on LLM safety and the need for improved defense mechanisms. This work aims to provide a thorough understanding of the current landscape of red-teaming attacks and defenses on LLMs, enabling the development of more secure and reliable language models.
title Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.09097