Cat and Mouse in the LLM Era: An Investigation of Jailbreak Attacks and Defenses

Large Language Models (LLMs) are susceptible to jailbreak assaults that can circumvent safety alignment and produce destructive outputs, notwithstanding their impressive performance in a variety of natural language processing applications. This paper provides a systematic survey of the attack methods and defense mechanisms of jailbreaking attack for LLMs. Existing attacks fall into three categories: attacks that manipulate input content at the prompt level, attacks that leverage algorithmic search through optimization, and attacks in which artificial intelligence systems act as self-directed adversaries through autonomous reasoning. Then, the defense strategies are reviewed and categorized into prompt-level defenses, model-level defenses, and proactive system-level defenses. The review highlights that while substantial progress has been made, existing defenses are often unable to balance safety with model utility, and generalize poorly to novel attack strategies. This paper also discusses open challenges and promising directions for future research such as layered defense architectures and proactive mechanisms that interfere with the attack process itself.

Authors

Institutions

Publication Details

Journal
Applied and Computational Engineering
Published
2026-11-17
DOI
https://doi.org/10.54254/2755-2721/2026.39016
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Cat and Mouse in the LLM Era: An Investigation of Jailbreak Attacks and Defenses

Puhan Chen
3 links
Applied and Computational Engineering
Adversarial Robustness in Machine Learning
article

Cat and Mouse in the LLM Era: An Investigation of Jailbreak Attacks and Defenses

Puhan Chen
article en

Abstract

Large Language Models (LLMs) are susceptible to jailbreak assaults that can circumvent safety alignment and produce destructive outputs, notwithstanding their impressive performance in a variety of natural language processing applications. This paper provides a systematic survey of the attack methods and defense mechanisms of jailbreaking attack for LLMs. Existing attacks fall into three categories: attacks that manipulate input content at the prompt level, attacks that leverage algorithmic search through optimization, and attacks in which artificial intelligence systems act as self-directed adversaries through autonomous reasoning. Then, the defense strategies are reviewed and categorized into prompt-level defenses, model-level defenses, and proactive system-level defenses. The review highlights that while substantial progress has been made, existing defenses are often unable to balance safety with model utility, and generalize poorly to novel attack strategies. This paper also discusses open challenges and promising directions for future research such as layered defense architectures and proactive mechanisms that interfere with the attack process itself.

Applied and Computational EngineeringVol. 282(1)
City University of Hong Kong (HK)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon