Hijacking Large Language Models via Adversarial In-Context Learning
- 5 September 2026
- book chapter
- Published by Springer Nature
- p. 224-241
Abstract
No abstract availableKeywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Not All Tokens Are Meant to Be ForgottenProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Jailbreak and Guard Aligned Language Models With Only Few In-Context DemonstrationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models2024
- Membership Inference Attacks Against In-Context Learning2024
- Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks2024
- Learning Compact Features via In-Training Representation AlignmentProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Improving Adversarial Robustness via Probabilistically Compact Loss with Logit ConstraintsProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search2020
- TextBugger: Generating Adversarial Text Against Real-world Applications2019