paperJune 2025Unreviewed

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Yanxu Mao, Tiehan Cui, Peipei Liu, Datao You, Hongsong Zhu

arXiv.org

Abstract

Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a systematic survey of the growing complexity of jailbreak attacks and corresponding defense mechanisms within the expanding LLM ecosystem. We first trace the developmental trajectory from LLMs to MLLMs and Agents, highlighting the core security challenges emergin

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{mao2025from,
  title = {{From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem}},
  author = {Yanxu Mao and Tiehan Cui and Peipei Liu and Datao You and Hongsong Zhu},
  year = {2025},
  month = jun,
  eprint = {2506.15170},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2506.15170},
  url = {https://www.semanticscholar.org/paper/ccfabe9f33f11bd1fbc4ac2bf219fc29cc5fa96d}
}