This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned param…

This paper investigates the production-evaluation gap in Large Reasoning Models (LRMs), finding that while LRMs excel at generating solutions, they struggle significantly to evaluate flawed reasoning,…

The paper proposes a black-box attack using a hierarchical genetic algorithm to induce 'overthinking' in Large Reasoning Models, demonstrating that this vulnerability can cause significant resource ex…

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new s…

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks…

The paper introduces EditRisk-Bench, a novel benchmark designed to systematically evaluate the safety risks and downstream reasoning corruption caused by malicious knowledge editing in large language…

The paper introduces Jargon, a novel adversarial framework that exploits the vulnerability of LLMs to context-specific safety boundary blurring, achieving high attack success rates across multiple fro…

This paper introduces Ghostwriter, an attack framework demonstrating that LLMs are highly vulnerable to adopting misleading viewpoints when provided with fabricated, yet credible-looking, evidence.

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated in…

Defense training for LLM agents, intended to improve safety, systematically degrades their core competence, leading to unreliability in multi-step tasks.

The paper introduces Critical-CoT, a novel two-stage fine-tuning defense framework that equips LLMs with critical thinking abilities to detect and reject malicious reasoning steps introduced by advanc…

The paper introduces a challenging benchmark for LLM agents to perform unsupervised threat hunting on raw Windows event logs, finding that current frontier models perform poorly and are not ready for…

The paper proposes a deterministic, version-aware aggregation method that significantly outperforms existing LLM-based systems for resolving memory conflicts in fact consolidation tasks.

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

The paper introduces an automatic numeric-remapping attack to test the robustness of LLMs on arithmetic word problems, finding that LLMs remain sensitive to small numeric changes in datasets like GSM8…

The paper identifies the Misattribution Gap, showing that memory-layer attacks (Semantic Norm Drift) can mimic model failure in multi-agent AI systems, and proposes novel detection and mitigation tech…