Semantic Isomorphism Attacks and Defense Evaluation for Jailbreaking Large Language Models
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 4303-4318
Abstract
No abstract availableFunding Information
- National Key Program of the National Natural Science Foundation of China (82430108)
- National Key Research and Development Program of China (2026ZD0125300)
This publication has 19 references indexed in Scilit:
- Jailbreak and Guard Aligned Language Models With Only Few In-Context DemonstrationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
- Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression2026
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Boosting Jailbreak Attack with Momentum2025
- DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak2025
- Stronger Universal and Transferable Attacks by Suppressing Refusals2025
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models2024
- Exploring the Robustness of Decision-Level Through Adversarial Attacks on LLM-Based Embodied Models2024
- A Hitchhiker’s Guide to Jailbreaking ChatGPT via Prompt Engineering2024