This study compares two methods of safety unalignment (Jailbreak-Tuning and Weight Orthogonalization) across six LLMs and finds that Weight Orthogonalization (WO) significantly enhances malicious capa…

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 proposes Ablating Safety, a controlled protocol for removing safety alignment from language models, demonstrating that targeted de-alignment can significantly boost security performance whil…

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM s…

The paper introduces ML-Bench, a policy-grounded multilingual safety benchmark, and ML-Guard, a superior guardrail model that enables culturally and legally aligned safety assessment for LLMs across 1…

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 challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits t…

The paper introduces SABER, a new benchmark that evaluates the operational safety of LLM coding agents in complex, stateful project environments, finding that current models have a high rate of harmfu…

This paper shifts the focus of LLM safety from preventing misalignment to investigating the model's intrinsic ability to self-recover its alignment after being corrupted by adversarial inputs.

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…

The paper conducts an interpretability-driven safety audit of eight state-of-the-art LLMs, demonstrating that while interpretability-based steering is a powerful auditing tool, model robustness varies…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper introduces SecureBreak, a manually annotated, safety-oriented dataset designed to help detect harmful outputs from large language models (LLMs) that bypass existing security alignments.

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

The paper introduces POLARIS, a novel framework that systematically generates comprehensive and verifiable safety tests for LLMs by formalizing natural language policies into First-Order Logic and exp…

The paper proposes the Expected Safety Impact (ESI) framework to identify safety-critical parameters in LLMs, introducing targeted tuning methods (SET and SPA) to enhance safety and preserve alignment…

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 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 identifies and measures a critical failure mode where LLM agents violate policies by losing or corrupting directive-bearing state during the process of assembling the decision context, and p…