Awesome LLM Security

Key papers

• Adversarial Machine Learning Attacks And Defense Methods In The Cyber Security Domain (2020)
  Ihai Rosenberg, Asaf Shabtai, Yuval Elovici, et al.
  17.66
• Injecagent: Benchmarking Indirect Prompt Injections In Tool-integrated Large Language Model Agents (2024)
  Qiusi Zhan, Zhixiang Liang, Zifan Ying, et al.
  15.95
• Cyberlearning: Effectiveness Analysis Of Machine Learning Security Modeling To Detect Cyber-anomalies And Multi-attacks (2021)
  Iqbal H. Sarker
  15.10
• A Survey On Explainable Artificial Intelligence For Cybersecurity (2023)
  Gaith Rjoub, Jamal Bentahar, Omar Abdel Wahab, et al.
  14.90
• Exploiting Programmatic Behavior Of Llms: Dual-use Through Standard Security Attacks (2023)
  Daniel Kang, Xuechen Li, Ion Stoica, et al.
  13.70
• Security Vulnerability Detection Using Deep Learning Natural Language Processing (2021)
  Noah Ziems, Shaoen Wu
  13.55
• Generative AI In Cybersecurity: A Comprehensive Review Of LLM Applications And Vulnerabilities (2024)
  Mohamed Amine Ferrag, Fatima Alwahedi, Ammar Battah, et al.
  13.17
• Large Language Models In Cybersecurity: State-of-the-art (2024)
  Farzad Nourmohammadzadeh Motlagh, Mehrdad Hajizadeh, Mehryar Majd, et al.
  11.85
• Prompt As Triggers For Backdoor Attack: Examining The Vulnerability In Language Models (2023)
  Shuai Zhao, Jinming Wen, Luu Anh Tuan, et al.
  11.85
• CIPHER: Cybersecurity Intelligent Penetration-testing Helper For Ethical Researcher (2024)
  Derry Pratama, Naufal Suryanto, Andro Aprila Adiputra, et al.
  11.78
• Learn To Adapt: Robust Drift Detection In Security Domain (2022)
  Aditya Kuppa, Nhien-An Le-Khac
  11.58
• Llms In Software Security: A Survey Of Vulnerability Detection Techniques And Insights (2025)
  Ze Sheng, Zhicheng Chen, Shuning Gu, et al.
  11.54
• Exploring The Dark Side Of AI: Advanced Phishing Attack Design And Deployment Using Chatgpt (2023)
  Nils Begou, Jeremy Vinoy, Andrzej Duda, et al.
  11.29
• Deep Reinforcement Learning For Cybersecurity Threat Detection And Protection: A Review (2022)
  Mohit Sewak, Sanjay K. Sahay, Hemant Rathore
  11.29
• Poisonprompt: Backdoor Attack On Prompt-based Large Language Models (2023)
  Hongwei Yao, Jian Lou, Zhan Qin
  11.19
• Fedsecurity: Benchmarking Attacks And Defenses In Federated Learning And Federated Llms (2023)
  Shanshan Han, Baturalp Buyukates, Zijian Hu, et al.
  10.85
• Enhancing Threat Detection Using Artificial Intelligence in Modern Cybersecurity Systems Using SPSS Statistics (2026)
  Rajendar Dommeti
  10.82
• Towards Explainable Network Intrusion Detection Using Large Language Models (2024)
  Paul R. B. Houssel, Priyanka Singh, Siamak Layeghy, et al.
  10.74
• DOLOS: A Novel Architecture For Moving Target Defense (2023)
  Giulio Pagnotta, Fabio de Gaspari, Dorjan Hitaj, et al.
  10.74
• Machine Learning (in) Security: A Stream Of Problems (2020)
  Fabrício Ceschin, Marcus Botacin, Albert Bifet, et al.
  10.61
• Ctibench: A Benchmark For Evaluating Llms In Cyber Threat Intelligence (2024)
  Md Tanvirul Alam, Dipkamal Bhusal, Le Nguyen, et al.
  10.48
• Living-off-the-land Command Detection Using Active Learning (2021)
  Talha Ongun, Jack W. Stokes, Jonathan Bar Or, et al.
  10.48
• Next-generation Phishing: How LLM Agents Empower Cyber Attackers (2024)
  Khalifa Afane, Wenqi Wei, Ying Mao, et al.
  10.35
• Logpr\'ecis: Unleashing Language Models For Automated Malicious Log Analysis (2023)
  Matteo Boffa, Rodolfo Vieira Valentim, Luca Vassio, et al.
  10.21
• On The (in)security Of Peer-to-peer Decentralized Machine Learning (2022)
  Dario Pasquini, Mathilde Raynal, Carmela Troncoso
  10.07
• Tackling Imbalanced Data In Cybersecurity With Transfer Learning: A Case With ROP Payload Detection (2021)
  Haizhou Wang, Peng Liu
  9.92
• Enhancing 6G-IoT Network Security: A Trustworthy and Responsible AI-Driven Stacked-Hybrid Model for Attack Detection (2026)
  Anshika Sharma et al.
  9.81
• Illuminati: Towards Explaining Graph Neural Networks For Cybersecurity Analysis (2023)
  Haoyu He, Yuede Ji, H. Howie Huang
  9.41
• With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks And Defenses For Linear Regression Models (2020)
  Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue, et al.
  9.23
• Modsec-learn: Boosting Modsecurity With Machine Learning (2024)
  Christian Scano, Giuseppe Floris, Biagio Montaruli, et al.
  9.16
• NYU CTF Bench: A Scalable Open-source Benchmark Dataset For Evaluating Llms In Offensive Security (2024)
  Minghao Shao, Sofija Jancheska, Meet Udeshi, et al.
  8.85
• Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, And Improvements (2024)
  Isamu Isozaki, Manil Shrestha, Rick Console, et al.
  8.82
• Intrusion Detection System Using Deep Learning For Network Security (2025)
  Soham Chatterjee, Satvik Chaudhary, Aswani Kumar Cherukuri
  8.65
• A Survey Of Source Code Representations For Machine Learning-based Cybersecurity Tasks (2024)
  Beatrice Casey, Joanna C. S. Santos, George Perry
  8.60
• Membership Inference Attacks Against In-context Learning (2024)
  Rui Wen, Zheng Li, Michael Backes, et al.
  8.35
• APT-LLM: Embedding-based Anomaly Detection Of Cyber Advanced Persistent Threats Using Large Language Models (2025)
  Sidahmed Benabderrahmane, Petko Valtchev, James Cheney, et al.
  8.23
• On Security And Sparsity Of Linear Classifiers For Adversarial Settings (2017)
  Ambra Demontis, Paolo Russu, Battista Biggio, et al.
  7.81
• Large Language Model (LLM) For Software Security: Code Analysis, Malware Analysis, Reverse Engineering (2025)
  Hamed Jelodar, Samita Bai, Parisa Hamedi, et al.
  7.24
• Autonomous Threat Detection And Response In Cloud Security: A Comprehensive Survey Of Ai-driven Strategies (2026)
  Gaurav Sarraf, Vibhor Pal
  7.24
• Feasibility Study For Supporting Static Malware Analysis Using LLM (2024)
  Shota Fujii, Rei Yamagishi
  7.16
• Fine-tuned Large Language Models (llms): Improved Prompt Injection Attacks Detection (2024)
  Md Abdur Rahman, Fan Wu, Alfredo Cuzzocrea, et al.
  7.16
• Leveraging Large Language Models To Detect Npm Malicious Packages (2024)
  Nusrat Zahan, Philipp Burckhardt, Mikola Lysenko, et al.
  7.16
• Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks On Pre-trained Model Hubs (2024)
  Jian Zhao, Shenao Wang, Yanjie Zhao, et al.
  7.16
• A Comparative Analysis Of Dnn-based White-box Explainable AI Methods In Network Security (2025)
  Osvaldo Arreche, Mustafa Abdallah
  7.06
• Security Concerns For Large Language Models: A Survey (2025)
  Miles Q. Li, Benjamin C. M. Fung
  7.06
• Research On Enhancing Cloud Computing Network Security Using Artificial Intelligence Algorithms (2025)
  Yuqing Wang, Xiao Yang
  7.06
• A Dynamic-adversarial Mining Approach To The Security Of Machine Learning (2018)
  Tegjyot Singh Sethi, Mehmed Kantardzic, Lingyu Lyua, et al.
  6.77
• Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks (2026)
  John T. Halloran et al.
  6.69
• Genxss: An Ai-driven Framework For Automated Detection Of XSS Attacks In Wafs (2025)
  Vahid Babaey, Arun Ravindran
  6.64
• Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks On LLM Agents (2025)
  Qiusi Zhan, Richard Fang, Henil Shalin Panchal, et al.
  6.39
• Autoredteamer: Autonomous Red Teaming With Lifelong Attack Integration (2025)
  Andy Zhou, Kevin Wu, Francesco Pinto, et al.
  6.39
• Vulscriber: Exploring Rag-based Vulnerability Augmentation With Llms (2024)
  Seyed Shayan Daneshvar, Yu Nong, Xu Yang, et al.
  6.34
• APOLLO: A Gpt-based Tool To Detect Phishing Emails And Generate Explanations That Warn Users (2024)
  Giuseppe Desolda, Francesco Greco, Luca Viganò
  6.34
• Psyborg+: Modeling And Simulation For Detecting Cognitive Biases In Advanced Persistent Threats (2024)
  Shuo Huang, Fred Jones, Nikolos Gurney, et al.
  6.34
• Spearbot: Leveraging Large Language Models In A Generative-critique Framework For Spear-phishing Email Generation (2024)
  Qinglin Qi, Yun Luo, Yijia Xu, et al.
  6.34
• Harmbench: A Standardized Evaluation Framework For Automated Red Teaming And Robust Refusal (2024)
  Mantas Mazeika, Long Phan, Xuwang Yin, et al.
  5.95
• Secalign: Defending Against Prompt Injection With Preference Optimization (2024)
  Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar, et al.
  5.84
• UOR: Universal Backdoor Attacks On Pre-trained Language Models (2023)
  Wei Du, Peixuan Li, Boqun Li, et al.
  5.84
• Community Targeted Phishing: A Middle Ground Between Massive And Spear Phishing Through Natural Language Generation (2017)
  Alberto Giaretta, Nicola Dragoni
  5.84
• Automatically Generating Rules Of Malicious Software Packages Via Large Language Model (2025)
  Xiangrui Zhang, Haoyu Chen, Yongzhong He, et al.
  5.82