LLM-Based Jailbreak Attack Detection and Security: A Layered Review and Framework

Large language models (LLMs) are now used in search, coding assistants, customer support and autonomous agents. They are trained to refuse harmful requests, but jailbreak attacks can still push them past those safeguards. This paper studies that problem and proposes a practical way to defend against it. The paper first reviews the main jailbreak attack families: gradient-based adversarial suffixes, prompts generated by attacker models, persona and role-play templates, many-shot and multi-turn escalation, encoding and multilingual tricks, and multimodal or agent-based prompt injection. It then compares the main detection and defense methods by where they act (input, model or output), including perplexity filters, perturbation checks, guard classifiers, safety fine-tuning, instruction hierarchies and output monitors, and it identifies five research gaps in the current work. To address these gaps, the paper proposes a layered detection and security framework with six modules: policy and threat modeling, input screening, a hardened model, an output monitor, agent action control, and a logging and feedback loop with continuous red-teaming. A risk-based routing scheme limits latency and cost. The paper also defines a three-phase evaluation protocol (detector testing, attack-suite testing and adaptive testing) that measures attack success rate, false refusal rate, latency and attacker cost together, using multiple judges. This is a literature-based review and design study. It reports no new experimental results, and the framework has not yet been implemented. Keywords: Large Language Models, Jailbreak Attacks, Prompt Injection, Safety Alignment, Guardrails, Red Teaming, AI Security

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24359992
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

LLM-Based Jailbreak Attack Detection and Security: A Layered Review and Framework

Vaibhav Sawalkar, Vedant Jadhav, Parth Ubhad, Ujjwal Baviskar et al.
Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
article

LLM-Based Jailbreak Attack Detection and Security: A Layered Review and Framework

Vaibhav Sawalkar, Vedant Jadhav, Parth Ubhad, Ujjwal Baviskar, Mohit Patil
article en

Abstract

Large language models (LLMs) are now used in search, coding assistants, customer support and autonomous agents. They are trained to refuse harmful requests, but jailbreak attacks can still push them past those safeguards. This paper studies that problem and proposes a practical way to defend against it. The paper first reviews the main jailbreak attack families: gradient-based adversarial suffixes, prompts generated by attacker models, persona and role-play templates, many-shot and multi-turn escalation, encoding and multilingual tricks, and multimodal or agent-based prompt injection. It then compares the main detection and defense methods by where they act (input, model or output), including perplexity filters, perturbation checks, guard classifiers, safety fine-tuning, instruction hierarchies and output monitors, and it identifies five research gaps in the current work. To address these gaps, the paper proposes a layered detection and security framework with six modules: policy and threat modeling, input screening, a hardened model, an output monitor, agent action control, and a logging and feedback loop with continuous red-teaming. A risk-based routing scheme limits latency and cost. The paper also defines a three-phase evaluation protocol (detector testing, attack-suite testing and adaptive testing) that measures attack success rate, false refusal rate, latency and attacker cost together, using multiple judges. This is a literature-based review and design study. It reports no new experimental results, and the framework has not yet been implemented. Keywords: Large Language Models, Jailbreak Attacks, Prompt Injection, Safety Alignment, Guardrails, Red Teaming, AI Security

Zenodo (CERN European Organization for Nuclear Research)
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