# Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks

arXiv: https://arxiv.org/abs/2408.15207 · HTML: https://mlsanity.com/paper/2408.15207/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 42)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://mlsanity.com/paper/2308.07308/) (2023)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models](https://mlsanity.com/paper/2310.15140/) (2023)
- [ReCode: Robustness Evaluation of Code Generation Models](https://mlsanity.com/paper/2212.10264/) (2022)
- [Can GPT-3 Perform Statutory Reasoning?](https://mlsanity.com/paper/2302.06100/) (2023)
- [TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing](https://mlsanity.com/paper/1807.10875/) (2018)
- [Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning](https://mlsanity.com/paper/2402.08416/) (2024)
- [Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons](https://mlsanity.com/paper/2406.14144/) (2024)
- [Perception-guided Jailbreak against Text-to-Image Models](https://mlsanity.com/paper/2408.10848/) (2024)
- [PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition](https://mlsanity.com/paper/2405.07932/) (2024)

## Built on by (most cited first, 8 of 8)

- [Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics](https://mlsanity.com/paper/2504.00446/) (2025)
- [Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering](https://mlsanity.com/paper/2508.11824/) (2025)
- [Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation](https://mlsanity.com/paper/2507.08020/) (2025)
- [ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents](https://mlsanity.com/paper/2605.22321/) (2026)
- [Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs](https://mlsanity.com/paper/2509.17314/) (2025)
- [Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads](https://mlsanity.com/paper/2603.05772/) (2026)
- [Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks](https://mlsanity.com/paper/2511.00346/) (2025)
- [RACC: Representation-Aware Coverage Criteria for LLM Safety Testing](https://mlsanity.com/paper/2602.02280/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have revolutionized artificial intelligence, but their increasing deployment across critical domains has raised concerns about their abnormal behaviors when faced with malicious attacks. Such vulnerability alerts the widespread inadequacy of pre-release testing. In this paper, we conduct a comprehensive empirical study to evaluate the effectiveness of traditional coverage criteria in identifying such inadequacies, exemplified by the significant security concern of jailbreak attacks. Our study begins with a clustering analysis of the hidden states of LLMs, revealing that the embedded characteristics effectively distinguish between different query types. We then systematically evaluate the performance of these criteria across three key dimensions: criterion level, layer level, and token level. Our research uncovers significant differences in neuron coverage when LLMs process normal versus jailbreak queries, aligning with our clustering experiments. Leveraging these findings, we propose three practical applications of coverage criteria in the context of LLM security testing. Specifically, we develop a real-time jailbreak detection mechanism that achieves high accuracy (93.61% on average) in classifying queries as normal or jailbreak. Furthermore, we explore the use of coverage levels to prioritize test cases, improving testing efficiency by focusing on high-risk interactions and removing redundant tests. Lastly, we introduce a coverage-guided approach for generating jailbreak attack examples, enabling systematic refinement of prompts to uncover vulnerabilities. This study improves our understanding of LLM security testing, enhances their safety, and provides a foundation for developing more robust AI applications.