IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts
- 5 September 2024
- book chapter
- Published by Springer Nature
- p. 146-165
Abstract
No abstract availableKeywords
This publication has 16 references indexed in Scilit:
- Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks2024
- FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models2024
- Can Large Language Models Provide Security & Privacy Advice? Measuring the Ability of LLMs to Refute Misconceptions2023
- Role play with large language modelsNature, 2023
- AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics2023
- Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots2023
- From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and PrivacyIEEE Access, 2023
- Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts2023
- Why So Toxic?2022
- Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm2021