LLMs for Cybersecurity

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 280% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 166

All topics

Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
Oct 7, 2026Georgios Koutidis, Nikolaos Kekatos, Tom Nianios +1LLMs for Cybersecurity Tool Access Control for LLM Agents
Clone Systems, Larnaca, Cyprus · University of Thessaly, Department of Intelligent Energy Systems, Larissa, Greece
MARS: Malware Analysis with Rule-Based Scoring of LLM Claims
Oct 7, 2026Hyeongjun ChoiMalware Classification LLMs for Cybersecurity
78ResearchLab, 8, Yangpyeong-ro 25-gil, Yeongdeungpo-gu, Seoul, 07207, Republic of Korea
Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering
Oct 6, 2026Kemal Davaslioglu, Sastry KompellaLLMs for Cybersecurity
Nexcepta, Gaithersburg, MD, USA
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
Oct 5, 2026Tobias Heldt, Matt Turk, Christoph Landolt +1Automated Program Repair Cybersecurity
XOR · Protege · CISPA Helmholtz Center for Information Security
Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning
Oct 5, 2026Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni +1LLM Auditing Software Vulnerability Detection
Carnegie Mellon University, Pittsburgh, Pennsilvanya, USA
AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models
Oct 4, 2026Bao-Phong Nguyen, Gia-Khanh Pham, Thai-Duong Do +7Network Intrusion Detection LLMs for Cybersecurity
Business AI Lab, College of Technology, National Economics University, Hanoi, Vietnam
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Oct 1, 2026Pengfei Li, Naufal Suryanto, Sicheng Zhang +1LLMs for Cybersecurity LLM Tool Use
Khalifa University · University of Western Australia
HydroJEV: A one-second, training-free screen for cyber-attack and fault attribution in water distribution networks
Oct 1, 2026Tianwei Mu, Shengyan Jiang, Mingzhe Yuan +5Cybersecurity LLMs for Cybersecurity
School of Municipal Engineering and Environment, Shenyang Jianzhu University, Shenyang 110168, China · Guangzhou Institute of Industrial Intelligence, Guangzhou 510000, China · Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China +2
Jev-IDS: System One Models for Network Intrusion Detection
Oct 1, 2026Paulo Severo, Silvio E. Quincozes, Amanda DiasNetwork Intrusion Detection LLMs for Cybersecurity
Graduate Program in Software Engineering, Federal University of Pampa (UNIPAMPA), Alegrete, Rio Grande do Sul, Brazil
Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution
Sep 30, 2026Harshith Doppalapudi, Nathaniel D. Bastian, Ankit ShahAutonomous Cyber Defense Language Model-Based Control
Indiana University Bloomington, IN, USA · Johns Hopkins University Baltimore, MD, USA
No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents
Sep 30, 2026Ayan Javeed Shaikh, Arunesh Sinha, Nathaniel D. Bastian +1LLM Red Teaming AI Agent Evaluation
Indiana University Bloomington, IN, USA · Rutgers University Piscataway, NJ, USA · Johns Hopkins University Baltimore, MD, USA
APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry
Sep 30, 2026Yu Wang, Shuhao Li, Tao Yin +4Distribution Shift Robustness AI Agent Benchmarks
Zhongguancun Laboratory
HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents
Sep 27, 2026Zhuowen Liu, Zhixuan WangLLMs for Cybersecurity LLM Agent Reliability
Cybersecurity Lab Japan Advanced Institute of Science and Technology (JAIST) Nomi, Ishikawa, Japan · College of Fine Arts Liaoning Normal University Dalian, Liaoning, China
Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
Sep 23, 2026Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia +2Agent Failure Analysis LLM Agent Evaluation
Cybersecurity, DTRC, National Research Council, Ottawa, Canada · University of Windsor, Windsor, Ontario, Canada
Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
Sep 22, 2026Om Nepal, Sushant Aryal, Oluseyi Olukola +1Automated Program Repair LLMs for Cybersecurity
School of Computing Sciences and Computer Engineering, The University of Southern Mississippi, Hattiesburg, MS 39406, USA
ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers
Sep 17, 2026Hyeongjun Choi, Wonyoung Jung, Haehoon Seo +1Adversarial Attacks on LLMs LLM Security
78ResearchLab Seoul, South Korea
MiST: Mid-Training LLMs for Cybersecurity
Sep 16, 2026Oded Ovadia, Elad Ben Zaken, Elad Guttman +1Synthetic Data Pretraining Domain-Adaptive Pretraining
Dream
PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs
Sep 16, 2026Rushabh Vipulkumar Patel, Dipo Dunsin, Mohammed Almaiah +1Automated Penetration Testing LLMs for Cybersecurity
Computer Security Laboratory, University of Wales Trinity Saint David, London, United Kingdom · King Abdullah IT School, The University of Jordan, Amman, Jordan · School of Computer Science and Mathematics, Keele University, Newcastle-under-Lyme, United Kingdom
Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale
Sep 14, 2026Aman Priyanshu, Supriti Vijay, Kimia Majd +8Software Vulnerability Detection AI Agent Security
1Foundation AI–Cisco Systems Inc. · 3Carnegie Mellon University · †Work done while at Foundation AI +1
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
Sep 12, 2026Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros +3Cybersecurity Indirect Prompt Injection
Aristotle University of Thessaloniki, Greece · Clone Systems, Cyprus
Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks
Sep 11, 2026Sebastiano Nordio, Michele LottoCybersecurity Small Language Models
Independent · University of Genoa, Via All’Opera Pia, 16145 Genoa, Italy
Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports
Sep 8, 2026Akash Prakash, Boubakr Nour, Makan Pourzandi +2Retrieval-Augmented Generation Cyber Threat Intelligence
Concordia University, Canada · Ericsson Security Research, Canada
Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks
Sep 8, 2026Aymene Berriche, Cathrine Shalby, Mohannad Alhanahnah +1LLM Evaluation LLM Auditing
Qatar Computing Research Institute, HBKU
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Sep 8, 2026Zongjie Li, Alan Z. W, John Nicolas J +4Training Data Curation Cybersecurity
Vera Praxis Lab
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3LLM Safety Benchmarks LLM Refusal Behavior
Johns Hopkins University
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Aug 24, 2026Jian Yang, Haau-Sing Li, Shawn Guo +10Cybersecurity Software Security
Beihang University · ELLIS · IQuest Research +1
LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles
Aug 13, 2026Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1Automated Software Testing Software Vulnerability Detection
Department of Civil, Construction & Environmental Engineering, The University of Alabama 2009 Smart Communities and Innovation Building (SCIB), 28 Kirkbride Lane, Tuscaloosa, AL 35487-0288 · Department of Computer Science, The University of Alabama 3017 Cyber Hall, 248 Kirkbride Lane, Tuscaloosa, AL 35487-0288
The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
Aug 11, 2026Jeremy Spence, Nicholas Assaderaghi, Feng Xiao +9Software Reverse Engineering AI Agent Security Benchmarks
Columbia University · UC Berkeley · Vals AI +2
RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges
Aug 10, 2026Hanlin Jiang, Puyi Wang, Jiandong Jin +10Cybersecurity Automated Penetration Testing
Key Laboratory of High Confidence Software Technologies, Peking University, Ministry of Education · Huawei Technologies Co., Ltd. · Southeast University
Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence
Aug 7, 2026Jiayun Zhang, Junshen Xu, Zejun Xie +1Cyber Threat Intelligence Cybersecurity
Amazon Web Services New York, New York, USA · Amazon Web Services Boston, Massachusetts, USA · Rutgers University Piscataway, New Jersey, USA

Oct 7, 2026, cs.CRJ/K move · Enter open · S save

Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy

Georgios Koutidis, Nikolaos Kekatos, Tom Nianios, Alexios Lekidis

Clone Systems, Larnaca, Cyprus · University of Thessaly, Department of Intelligent Energy Systems, Larissa, Greece

LLMs for Cybersecurity Tool Access Control for LLM Agents Prompt Injection Attacks on AI Agents LLM Guardrails AI Agent Security Benchmarks

Open paper AskPDF arXiv

Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few analysts. Large Language Models (LLMs) are increasingly proposed as reasoning engines that triage alerts and, in autonomous deployments, issue commands that block IPs, kill processes, or quarantine files on production hosts. This coupling introduces a new risk: a single adversarial alert can become a remote code path through the LLM's reasoning, leading it to recommend an action the SOC then executes. We present a constrained-action architecture with two coordinated layers: (i) a SIEM/XDR control plane that grounds remediation in correlated host events and confines the LLM's output to a closed intent vocabulary whose templated commands are executed by thin endpoint agents, backstopped by an argument validator; and (ii) a NeMo-Guardrails proxy that wraps the SOC-analyst LLM with input- and output-rail policies, evaluated out-of-the-box against a SOC-specific adversarial corpus we release. The stock proxy lifts injection recall from 25.0% to 94.5% at a 0.1% false-positive rate, and a live red-team exercise confirms that the closed intent vocabulary and argument validator contain the observed LLM failure modes before any command crosses the trust boundary. As an architectural fit (not yet a measured operational-technology deployment), the constrained-action property suits critical-infrastructure settings where a wrong remediation has physical, not merely operational, consequences. The loop is best run human-in-the-loop or delayed: the measured rail latency keeps inline control out of scope.

Momentum

Related topics

Latest papers 166