Pith. sign in

REVIEW 13 cited by

When LLMs Meet Cybersecurity: A Systematic Literature Review

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.03644 v2 pith:KC4AP537 submitted 2024-05-06 cs.CR cs.AI

classification cs.CRcs.AI
keywords llmscybersecurityresearchaddressesapplicationareacomprehensiveliterature
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The rapid development of large language models (LLMs) has opened new avenues across various fields, including cybersecurity, which faces an evolving threat landscape and demand for innovative technologies. Despite initial explorations into the application of LLMs in cybersecurity, there is a lack of a comprehensive overview of this research area. This paper addresses this gap by providing a systematic literature review, covering the analysis of over 300 works, encompassing 25 LLMs and more than 10 downstream scenarios. Our comprehensive overview addresses three key research questions: the construction of cybersecurity-oriented LLMs, the application of LLMs to various cybersecurity tasks, the challenges and further research in this area. This study aims to shed light on the extensive potential of LLMs in enhancing cybersecurity practices and serve as a valuable resource for applying LLMs in this field. We also maintain and regularly update a list of practical guides on LLMs for cybersecurity at https://github.com/tmylla/Awesome-LLM4Cybersecurity.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cybersecurity Detection Classification with Reasoning-enabled Language Models

    cs.LG 2026-07 conditional novelty 6.0 of 10

    CoT-trained triage plus a separate reasoning calibrator reaches 82.6% accuracy and large high-confidence recall gains over direct-label LLM classifiers on real SOC detections.

  2. Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift

    cs.CR 2025-09 conditional novelty 6.0 of 10

    Small single-dimension perturbations to embeddings of high-risk tokens can flip aligned LLM responses from refusal to harmful output, and a search algorithm (SEP) locates such perturbations across models.

  3. Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    ETTA bypasses LLM safety refusals by learning a linear toxicity direction in the embedding space and attenuating it in word embeddings at inference time.

  4. Safety case template for frontier AI: A cyber inability argument

    cs.CY 2024-11 accept novelty 6.0 of 10

    A proof-of-concept safety case template formalizes an inability argument for offensive cyber risk using risk models, proxy tasks, and evaluation results.

  5. On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

    cs.CR 2026-08 conditional novelty 5.0 of 10

    A PRISMA-based survey of 85 papers shows agentic LLM security research is attack-heavy and perception-focused, leaving action-layer and code-execution risks understudied.

  6. Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction

    cs.AI 2024-12 conditional novelty 5.0 of 10

    Using both URLs and screenshots with API-based multimodal LLMs reaches 93-94% accuracy on a 1,000-site phishing test set, and a URL-first agentic cascade cuts API costs 2.6-4.2x with only minor accuracy loss.

  7. Cumplimiento del Reglamento (UE) 2024/1689 en rob\'otica y sistemas aut\'onomos: una revisi\'on sistem\'atica de la literatura

    cs.CY 2025-09 reject novelty 4.0 of 10

    A PRISMA review claims robotics research only partially meets EU AI Act requirements, with big gaps in transparency, human oversight, and traceability.

  8. Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

    cs.CR 2025-08 conditional novelty 4.0 of 10

    Foundation-Sec-8B-Instruct, an instruction-tuned 8B cybersecurity LLM, is released and claimed to beat Llama 3.1-8B-Instruct on CTIBench-RCM and CTIBench-MCQA while remaining competitive on general instruction-following.

  9. LAMeD: LLM-generated Annotations for Memory Leak Detection

    cs.SE 2025-05 conditional novelty 4.0 of 10

    LLM-generated function annotations for C/C++ memory management improved CodeQL and Cooddy memory leak detection from 5 to 10 known bugs across 43 targets, at the cost of a large increase in warnings.

  10. Multi-Agent Collaboration in Incident Response with Large Language Models

    cs.CL 2024-12 conditional novelty 4.0 of 10

    LLM-based multi-agent teams can play the Backdoors and Breaches incident response game, but evidence that team structure affects success is statistically weak.

  11. On the Surprising Efficacy of LLMs for Penetration-Testing

    cs.CR 2025-07 conditional novelty 3.0 of 10

    A critical review arguing that LLMs are surprisingly effective for penetration testing because the task is largely pattern-matching, while noting serious reliability, safety, and cost barriers to autonomous use.

  12. Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective

    cs.CR 2024-11 conditional novelty 2.0 of 10

    A structured survey of jailbreak prompts and layered defenses for large language models, with six illustrative case studies and no empirical evaluation.

  13. A Survey: Towards Privacy and Security in Mobile Large Language Models

    cs.CR 2025-09 conditional

    A survey of privacy and security challenges for mobile large language models, summarizing known attack types and defenses without introducing new results.

Pith tools