The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

NeuroTrace introduces a novel framework using Inference Provenance Graphs (IPGs) to analyze the information flow during deep neural network inference, demonstrating that this provenance provides a rob…

This paper provides the first longitudinal analysis of log-based detection rule evolution in public repositories, finding that rule changes reflect ongoing operational trade-offs rather than steady co…

MemLineage introduces a novel, cryptographically-backed defense mechanism that enforces a chain-of-custody for LLM agent memory, preventing untrusted or poisoned state from justifying sensitive action…

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

This paper quantifies the polymorphic capacity of a commercial LLM, demonstrating that it can cheaply generate large populations of structurally diverse, yet behaviorally equivalent, offensive code pa…

The paper introduces a robust, four-mechanism LLM pipeline that generates auditable, evidence-grounded structured trait records for hundreds of thousands of diverse species across multiple taxa.

The paper introduces 'causality laundering,' a novel security vulnerability in tool-calling LLM agents where adversaries exfiltrate information by probing denied actions, and proposes the Agentic Refe…

The paper introduces a robust streaming probing objective that requires multiple evidence tokens to support a prediction, significantly improving the detection of harmful intent in LLMs, especially in…

This paper systematically diagnoses the failure modes of linear deception probes in LLMs, finding that while single-direction probes are insufficient, multi-dimensional probes can recover robust detec…

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injecti…

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper introduces IdeaGene-Bench, a benchmark for scientific lineage reasoning and idea generation, which includes 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise G…

The study demonstrates that LLM safety alignment is non-monotonic across model generations, showing that Gemma 3 exhibits unexpectedly high vulnerability to adversarial attacks compared to both its pr…

The study demonstrates that safety alignment in LLMs is non-monotonic across model generations, showing that Gemma 3 exhibits a significantly higher attack success rate than both its predecessor and s…

The paper proposes PROVFUSION, a multi-view fusion framework that integrates anomaly signals from attribute, structure, and causality views to overcome the limitations of single node- or edge-centric…