Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Frank Weizhen, Hu, Chenhui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.00240
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917681767120896
author Liu, Frank Weizhen
Hu, Chenhui
author_facet Liu, Frank Weizhen
Hu, Chenhui
contents As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges of LLMs, focusing on two main areas: Prompt Hacking and Adversarial Attacks, each with specific types of threats. Under Prompt Hacking, we explore Prompt Injection and Jailbreaking Attacks, discussing how they work, their potential impacts, and ways to mitigate them. Similarly, we analyze Adversarial Attacks, breaking them down into Data Poisoning Attacks and Backdoor Attacks. This structured examination helps us understand the relationships between these vulnerabilities and the defense strategies that can be implemented. The survey highlights these security challenges and discusses robust defensive frameworks to protect LLMs against these threats. By detailing these security issues, the survey contributes to the broader discussion on creating resilient AI systems that can resist sophisticated attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Vulnerabilities and Protections in Large Language Models: A Survey
Liu, Frank Weizhen
Hu, Chenhui
Machine Learning
Computation and Language
Cryptography and Security
As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges of LLMs, focusing on two main areas: Prompt Hacking and Adversarial Attacks, each with specific types of threats. Under Prompt Hacking, we explore Prompt Injection and Jailbreaking Attacks, discussing how they work, their potential impacts, and ways to mitigate them. Similarly, we analyze Adversarial Attacks, breaking them down into Data Poisoning Attacks and Backdoor Attacks. This structured examination helps us understand the relationships between these vulnerabilities and the defense strategies that can be implemented. The survey highlights these security challenges and discusses robust defensive frameworks to protect LLMs against these threats. By detailing these security issues, the survey contributes to the broader discussion on creating resilient AI systems that can resist sophisticated attacks.
title Exploring Vulnerabilities and Protections in Large Language Models: A Survey
topic Machine Learning
Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2406.00240