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…

The paper outlines the potential for using generative AI to conduct large-scale, simulation-based experiments in literary studies, demonstrating initial results in generating constrained literary text…

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.

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, often failing when the mis…

The paper introduces SciIntBench, an adversarial benchmark that reveals that LLMs' adherence to research integrity norms is highly sensitive to how the misconduct is framed, failing particularly when…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

PHANTOM is a novel framework that generates highly convincing, context-aware honeytokens by incorporating deep organizational knowledge, significantly improving their believability and detection resis…

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

The paper argues that traditional identity-based reputation mechanisms are structurally inapplicable to language model agents because their mutable, modular nature makes them ontologically dissociativ…

This study compares various authorship attribution methods on Japanese web reviews, finding that while BERT fine-tuning performs best, TF-IDF+LR offers superior stability and efficiency for large-scal…

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).

This paper introduces Ghostwriter, an attack framework demonstrating that LLMs are highly vulnerable to adopting misleading viewpoints when provided with fabricated, yet credible-looking, evidence.

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

The paper introduces extsc{Ptah}, a multi-agent harness designed to improve verifiable multimodal deep research by orchestrating the entire report generation process, ensuring factual grounding and v…

This study quantifies the privacy risk of inferring sensitive personality traits from user interactions with LLM-based conversational agents, demonstrating that machine learning models can accurately…

Frontier language models involuntarily leak secret information through thematic elements in their writing, even when explicitly instructed to keep the secret hidden.

The paper introduces the Sovereign Context Protocol (SCP), an open-source, attribution-aware data access layer designed to standardize how Large Language Models (LLMs) connect to and track usage of hu…

The paper introduces a novel, per-token feature derived from how sampling temperature reshapes the token distribution, demonstrating it is a significantly stronger predictor of LLM creativity than sta…

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…

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels…