This paper demonstrates that YARA rules, even when stripped of metadata, contain enough stylistic information to accurately infer the original source repository, author, and even the malware family.

This study explores the effectiveness of Large Language Models in altering code stylometry and evaluates their impact on authorship attribution and functionality preservation.

The paper proposes a comprehensive benchmark to systematically audit how varying persona prompts and model choices affect the technical quality and social representativeness of scholar recommendations…

This paper evaluates the reliability of using Large Language Models (LLMs) as automated judges to assess the quality of other LLMs, finding a high correlation with human judgment when suitable prompts…

This paper proposes SIREN, an automated method for manipulating the rankings of web-augmented large language models by iteratively editing retrieved webpages and testing the effect on the model's reco…

The paper introduces a cross-encoder re-ranker trained on attribution scores to improve the retrieval of highly relevant citation passages for legal question answering, outperforming standard semantic…

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 a Deep Research pipeline that significantly improves literature search recall and demonstrates that human-curated citation lists are often unreliable and do not serve as a true gr…

This paper compares sparse and dense retrieval models for scientific claim-source retrieval on the CheckThat! 2026 benchmark. Translating claims into English and incorporating publication metadata imp…

The paper introduces TELL, a novel explainable AI-generated text detection architecture that provides detailed, human-understandable explanations for its scores, achieving competitive performance whil…

The paper proposes SafeReview, a co-evolutionary adversarial training framework that significantly improves the robustness of LLM-based peer review systems against sophisticated adversarial hidden pro…

AttnDiff introduces a data-efficient white-box framework that extracts intrinsic attention-based fingerprints to verify the provenance and detect unauthorized derivation of large language models (LLMs…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

This paper conducts a large-scale audit of human annotation reporting in NLP, finding that while reporting has improved, critical details needed to assess annotation validity, such as training and agr…

This paper characterizes the risk of covert influence—where a sender's hidden behavioral payload transfers to a receiver through undetectable carriers—across three common LLM interfaces, demonstrating…

The paper introduces PRAIB, a benchmark that demonstrates that LLM-generated peer reviews, while often verbose, systematically diverge from human norms by being less variable, positively biased, and f…

TTPrint proposes a novel diverge-then-converge framework for extracting MITRE ATT&CK techniques from CTI reports, significantly improving both recall and precision compared to existing methods.

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

The paper systematically evaluates advanced retrieval-augmented generation (RAG) architectures for Cyber Threat Intelligence (CTI), demonstrating that a hybrid graph-text approach significantly improv…