arXiv Machine Learning
Jun 9
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.
PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits
arXiv:2510. 17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate.
Related stories
arXiv AI
Jun 12
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
arXiv:2602. 13379v2 Announce Type: replace-cross Abstract: LLM-based agents are becoming increasingly capable, yet their safety lags behind.
arXiv AI
Aug 28
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
RedEvoAgent is a black-box red‑teaming agent that transforms cross‑case attack trajectories into concise, human‑readable attack skills. It evolves these skills by profiling tool effectiveness, attributing tool credit, and applying a validation ratchet to keep only improvements. Experiments demonstrate that RedEvoAgent outperforms fixed and agentic baselines, enhances tool efficiency, and transfers across attacker models and target execution harnesses.
arXiv AI
Jun 11
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.
arXiv AI
Jun 2
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
arXiv:2606. 01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination.
arXiv AI
Aug 18
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills
arXiv:2608. 16465v1 Announce Type: new Abstract: Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making them difficult to systematically integrate, reuse, and improve at scale.
arXiv Computation and Language
Aug 27
A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks
The paper introduces a self‑evolving defense framework for large language models that uses a persistent, cross‑interaction rule memory to adapt to new jailbreak attacks. When an attack succeeds, the system abstracts the failure into a method‑level rule that captures the structural attack wrapper, allowing the rule to generalize across an entire attack family. This memory‑based adaptation operates without parameter updates, works with both open‑weight and black‑box models, and has been shown to reduce attack success rates while preserving benign utility across multiple jailbreak families.
arXiv AI
Jun 19
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.
arXiv AI
Jul 3
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
arXiv:2507. 22063v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) for code generation (i.
arXiv AI
Aug 18
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.
arXiv AI
Sep 1
SIR: Self-improving Red-teaming for Compute Use Agents
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv AI
Aug 11
Automating Deception: Scalable Multi-Turn LLM Jailbreaks
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).