This paper proposes a unified evaluation framework for hate speech detection that systematically assesses model performance and explainability across various label and rationale representation spaces,…

The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

The paper proposes a unified, microservices-based platform that integrates endpoint telemetry and predictive NLP models to provide real-time, correlated alerting for security risks and hate speech.

The paper evaluates LLM-generated reactions to Spanish online news, finding that off-the-shelf models fail to accurately reproduce the measurable properties of real audience discourse, and even fine-t…

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…

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 demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.

AsmRAG is a novel framework that improves malware detection by treating it as an evidence-based retrieval task using a code-specialized LLM, achieving high accuracy while providing transparent forensi…

The paper proposes an Interpretive Audit Pipeline to evaluate LLMs for public comment analysis, arguing that measuring inter-model disagreement is crucial because standard accuracy metrics fail to det…

The paper introduces a synthetic dataset of multi-round conversations to detect conversational smishing, finding that XGBoost with TF-IDF features achieved the best performance (72.5% accuracy).

The paper introduces LinguIUTics, a system that significantly improves the classification of rare psychological defense mechanisms in conversational text by fine-tuning Qwen3-8B using specialized imba…

SERSEM introduces a selective entropy-weighted scoring framework to significantly improve Membership Inference Attacks (MIAs) against code LLMs by focusing on human-centric coding anomalies rather tha…

The paper proposes a novel, scalable technique using unique canary tokens to automatically and accurately identify which web scrapers are feeding data to specific Large Language Models (LLMs).

SALLIE introduces a lightweight, modal-agnostic runtime detection framework that effectively safeguards LLMs and VLMs against both textual and visual jailbreaks and prompt injections without performan…

PhishSigma++ is a novel entity-relation-based detector that improves malicious email detection by focusing on invariant functional relationships between typed entities, significantly outperforming tex…

RefineRAG introduces a novel word-level poisoning framework that significantly enhances knowledge poisoning attacks against RAG systems, achieving state-of-the-art effectiveness and transferability to…

The paper proposes 'Uncertainty,' a multiscale uncertainty estimator that focuses on low-probability tokens to improve the detection of AI-generated text by addressing boilerplate dominance and score…

The paper demonstrates that relying on strict regular-expression parsing for evaluating LLM-based security log classifiers introduces systematic errors, potentially causing a functional model to appea…