Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safe

arXiv:2607.20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question? This

arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2605.08778v1 Announce Type: new Abstract: Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns.

<p>The blind spot in current AI guardrails</p> <p>Guardrail middleware for AI agents is maturing fast. LangChain ships native guardrails. NeMo Guardrails and Guardrails AI are

arXiv:2603.25747v1 Announce Type: new Abstract: The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their

arXiv:2606.27698v1 Announce Type: cross Abstract: Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations. While this has been

arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information