Get started
Keyword

jailbreak attacks

Description: Attempts to circumvent safety controls in large language models by eliciting responses that violate their intended restrictions.
OpenAlex ID: keywords/jailbreak-attacks
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy
2023 · Maanak Gupta, Charankumar Akiri, et al. · IEEE Access · 797
PDF
Security and Privacy Challenges of Large Language Models: A Survey
2025 · Badhan Chandra Das, M. Hadi Amini, et al. · ACM Computing Surveys · 363
PDF
A contemporary review on chatbots, AI-powered virtual conversational agents, ChatGPT: Applications, open challenges and future research directions
2024 · Avyay Casheekar, Archit Lahiri, et al. · Computer Science Review · 213
Code of "Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs"
2023 · Zou, Andy, Wang, Zifan, et al. · arXiv (Cornell University) · 196
PDF
Defending ChatGPT against jailbreak attack via self-reminders
2023 · Yueqi Xie, Jingwei Yi, et al. · Nature Machine Intelligence · 150
PDF
MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots
2024 · Gelei Deng, Yi Liu, et al. · Network and Distributed System Security Symposium · 123
PDF
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
2024 · Fengqing Jiang, Zhangchen Xu, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 56
PDF
A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges
2025 · Andrew Brown, Muhammad Roman, et al. · Big Data and Cognitive Computing · 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
Maya-LLM-Defence: Sovereign Military LLM with Affective SNN Safety Substrate
2026 · Swaminathan, Venkatesh · Zenodo (CERN European Organization for Nuclear Research) · 47
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
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
2024 · Zhexin Zhang, Junxiao Yang, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 44
PDF
A Survey of Attacks on Large Vision–Language Models: Resources, Advances, and Future Trends
2025 · Daizong Liu, Mingyu Yang, et al. · IEEE Transactions on Neural Networks and Learning Systems · 43
PDF
FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models
2024 · Dongyu Yao, Jianshu Zhang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 43
PDF
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
2024 · Zhangchen Xu, Fengqing Jiang, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 40
PDF
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
2023 · Liu, Xiaogeng, Xu, Nan, et al. · arXiv (Cornell University) · 40
PDF
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
2023 · Robey, Alexander, Wong, Eric, et al. · arXiv (Cornell University) · 37
PDF
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
2024 · Seungju Han, Kavel Rao, et al. · neural information processing systems · 35
PDF
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
2025 · Zonghao Ying, Aishan Liu, et al. · IEEE Transactions on Information Forensics and Security · 29
PDF
Defending LLMs against Jailbreaking Attacks via Backtranslation
2024 · Yihan Wang, Zhouxing Shi, et al. · 28
PDF
JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
2025 · Junjie Chu, Yugeng Liu, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 25
PDF
Multilingual Jailbreak Challenges in Large Language Models
2023 · Deng, Yue, Zhang, Wenxuan, et al. · arXiv (Cornell University) · 25
PDF
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
2023 · Yu, Jiahao, Lin, Xingwei, et al. · arXiv (Cornell University) · 24
PDF
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
2024 · Wei Zhao, Zhe Li, et al. · 23
PDF
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
2024 · Nan Xu, Fei Wang, et al. · Findings of the Association for Computational Linguistics: NAACL · 21
PDF
Works count: 1,667
Citation count: 3,852
Year
Topic
Type