SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks
cs.CR
Submitted: 2026-08-02
Updated: 2026-09-12
Code: https://github.com/SiyuanLi00/INTACT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Constitutional AI: Harmlessness from AI Feedback
- WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
- PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition
- A Survey on Agentic Security: Applications, Threats and Defenses
- LLMs Get Lost In Multi-Turn Conversation
- A Survey on Multi-Turn Interaction Capabilities of Large Language Models
- Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
- Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
- Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
- Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
- Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search
- X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
- From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
- Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing
- Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
- SoK: Evaluating Jailbreak Guardrails for Large Language 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
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills