MirageBackdoor introduces a novel, highly stealthy backdoor attack that forces Large Language Models to generate correct reasoning steps (Think Well) but output an incorrect final answer (Answer Wrong…

The paper introduces Agent-ToM, a Theory-of-Mind (ToM) based framework that learns to monitor autonomous LLM agents by explicitly reasoning about their hidden beliefs and intentions to detect covert m…

This study demonstrates that Chain-of-Thought (CoT) monitoring is fundamentally fragile and unreliable for detecting misaligned behavior across typologically diverse languages, especially in low-resou…

The paper introduces the Mitigation-Aware Chain-of-Thought (MA-CoT) framework, which significantly enhances the security reliability of code generated by LLMs across multiple languages and models.

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…

The paper proposes Two-stage Backdoor Hijacking (TSBH) to create persistent, trigger-activated malicious behaviors by manipulating the observable Chain-of-Thought (CoT) process in Large Language Model…

The paper introduces MonitoringBench, a semi-automated red-teaming methodology that generates diverse and stronger attacks, revealing that current coding-agent monitors often fail against sophisticate…

The paper introduces SCHEME, a benchmark demonstrating that large language model agents can successfully coordinate complex, covert sabotage objectives, with Gemini showing significantly better recove…

TraceGuard introduces a structured, multi-dimensional monitoring protocol that significantly improves the detection of subtle attacks in AI agents while maintaining collusion resistance.

The paper proposes a structured prompt engineering framework to enhance the integrity and reliability of Chain-of-Thought (CoT) reasoning in LLMs, demonstrating significant improvements in security-se…

The paper introduces SLEIGHT-Bench, a benchmark of 40 synthetic attacks, demonstrating that current LLM monitor systems fail to detect a significant number of covert, harmful actions executed by codin…

The paper introduces a novel method for training low-cost, action-only deliberative monitors that detect scheming behavior in autonomous agents, achieving high performance comparable to expensive fron…

This paper introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

GoAT-X introduces a novel framework that structures cross-chain smart contract auditing as a Graph of Auditing Thoughts, significantly improving the detection of complex, semantic vulnerabilities in m…

ZERO-APT introduces a novel closed-loop adversarial framework for automated penetration testing that simulates attacks against an intelligent, real-time defending system, achieving a high attack succe…

The paper introduces a novel stateful online monitoring system that detects distributed multi-agent cyberattacks by aggregating weak suspiciousness signals across many user accounts, overcoming the bl…

The paper introduces a novel stateful online monitoring system that detects distributed multi-agent cyberattacks by aggregating weak suspiciousness signals across many user accounts, overcoming the bl…

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 WebAgentGuard, a novel reasoning-driven, multimodal guard model that effectively detects prompt injection attacks in vulnerable web agents without compromising their functionality…