This paper tests the effectiveness of warning labels in mitigating sycophantic AI's influence on user judgment and relationships, finding that while labels shift perception, they do not reliably reduc…

This systematic mapping survey reviews label-efficient approaches for code vulnerability detection, synthesizing five paradigm families and providing a decision guide to navigate trade-offs.

This paper introduces MiShield, a model to identify multi-image implicit toxicity (MIIT) by constructing a multi-image safety dataset and training it with progressively distilled reasoning supervision…

This paper investigates why self-harm prediction models struggle to generalize across different hospitals, finding that variations in local lexical expression and feature importance are the primary ca…

The paper introduces FoodGuardBench, a comprehensive benchmark and a specialized guardrail model (FoodGuard-4B) to rigorously test and mitigate the severe food safety risks posed by large language mod…

The study found that human judgment of logical fallacies is significantly biased by source labels (e.g., human vs. AI), while LLM evaluations remained comparatively stable across these source conditio…

This paper proposes a simple real-time monitor for LLMs that turns an external verifier signal into an alarm decision by thresholding, showing competitiveness with advanced monitors in mathematical re…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

The paper introduces Opir, an efficient family of encoder-based multi-task guardrail models that provides competitive safety classification performance across various tasks while maintaining a signifi…

The paper introduces an evidence-augmented machine learning approach to improve self-harm surveillance by analyzing Emergency Department triage notes, achieving high and transferable performance acros…

This paper investigates the survival of licenses in the supply chain of AI artifacts, finding that a large percentage of artifacts lack declared licenses and that obligation-bearing licenses have low…

The paper introduces ToxiAlert-Bench, a large-scale audio dataset that uniquely annotates both textual and paralinguistic sources of toxicity, and proposes a dual-head neural network that significantl…

This paper introduces HarmAmp, a new benchmark for multi-turn harm amplification, and proposes TrajSafe, a proactive monitoring system that significantly reduces harmfulness in LLM interactions while…

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-a…

This paper comparatively analyzes two automatic label error detection methods, Confident Learning and Dataset Cartography, demonstrating that targeted data filtering significantly improves model perfo…

GLiGuard introduces a compact, schema-conditioned bidirectional encoder that achieves state-of-the-art performance in LLM content moderation across multiple safety dimensions while drastically reducin…

The paper introduces SONAR, a prompt sanitization framework that uses natural language inference metrics to identify and remove malicious instructions injected into LLM prompts, achieving near-zero at…

The paper analyzes that while multimodal large language models (MLLMs) offer superior semantic understanding for image generation, this enhanced capability significantly increases safety risks, partic…