Get started
Keyword

LLM security

Description: The protection of large language models and their applications against attacks, vulnerabilities, unauthorized access, and related information risks.
OpenAlex ID: keywords/llm-security
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
2024 · Yifan Yao, Jinhao Duan, et al. · High-Confidence Computing · 1,066
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
2024 · Edoardo Debenedetti, Jie Zhang, et al. · neural information processing systems · 122
Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models
2025 · Jingwei Yi, Yueqi Xie, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 83
In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
2023 · Shen, Xinyue, Chen, Zeyuan, et al. · arXiv (Cornell University) · 76
PDF
Agentic Large Language Models, a Survey
2025 · Aske Plaat, Max Van Duijn, et al. · Journal of Artificial Intelligence Research · 74
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
2024 · Zihao Xu, Yi Liu, et al. · 69
PDF
A Comprehensive Overview of Backdoor Attacks in Large Language Models Within Communication Networks
2024 · Haomiao Yang, Kunlan Xiang, et al. · IEEE Network · 66
PDF
Transitioning from MLOps to LLMOps: Navigating the Unique Challenges of Large Language Models
2025 · Saurabh Pahune, Zahid Akhtar · Information · 64
PDF
Medical large language models are susceptible to targeted misinformation attacks
2024 · Tianyu Han, Sven Nebelung, et al. · npj Digital Medicine · 59
PDF
Guardrail Blind Spots on Turkish Prompt Injection: A Same-Set Miss-Rate Comparison of Four Guard Models
2023 · Inan, Hakan, Upasani, Kartikeya, et al. · arXiv (Cornell University) · 55
PDF
Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations
2026 · Zeming Wei, Yifei Wang, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 51
PDF
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
2023 · Shayegani, Erfan, Mamun, Md Abdullah Al, et al. · arXiv (Cornell University) · 45
PDF
PoisonPrompt: Backdoor Attack on Prompt-Based Large Language Models
2024 · Hongwei Yao, Jian Lou, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 44
PDF
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
2025 · Xinyi Hou, Yanjie Zhao, et al. · arXiv (Cornell University) · 43
PDF
A Survey on Model Context Protocol: Architecture, State-of-the-art, Challenges and Future Directions
2025 · Partha Pratim Ray · 40
PDF
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
2023 · Liu, Xiaogeng, Xu, Nan, et al. · arXiv (Cornell University) · 40
PDF
Organizational preparedness for the use of large language models in pathology informatics
2023 · Steven N. Hart, Noah G. Hoffman, et al. · Journal of Pathology Informatics · 37
On large language models safety, security, and privacy: A survey
2025 · Ran Zhang, Hong-Wei Li, et al. · Journal of Electronic Science and Technology · 36
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
2025 · Kuo-Han Hung, Ching-Yun Ko, et al. · Findings of the Association for Computational Linguistics: NAACL · 32
PDF
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming
2024 · Suyu Ge, Chunting Zhou, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 30
PDF
Large Language Models in Cybersecurity
2024 · Andrei Kucharavy, Octave Plancherel, et al. · Springer eBooks · 28
Defending LLMs against Jailbreaking Attacks via Backtranslation
2024 · Yihan Wang, Zhouxing Shi, et al. · 28
PDF
Goal-Guided Generative Prompt Injection Attack on Large Language Models
2024 · Chong Zhang, Mingyu Jin, et al. · Proceedings · 26
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks
2024 · Dario Pasquini, Martin Strohmeier, et al. · 26
PDF
Security concerns for Large Language Models: A survey
2025 · Miles Q. Li, Benjamin C.M. Fung · Journal of Information Security and Applications · 25
Works count: 1,218
Citation count: 3,700
Year
Topic
Type