Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks
cs.CR, cs.IT, cs.LG, math.IT
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/FTian-UArizona/Intent-Hiding-Jailbreaks
Terminology
Sources
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks
- How Many Instructions Can LLMs Follow at Once?
- The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
- A Theoretical Game of Attacks via Compositional Skills
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- Qwen3 Technical Report
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs