This paper introduces Stemma, a black-box LLM fingerprinting method that abstracts away surface-form variation and measures the inheritance of decision regions for reliable provenance testing.

This survey provides a systematic framework and taxonomy for evidence tracing and execution provenance in LLM agents, addressing the difficulty of verifying and auditing complex agent behaviors.

The paper introduces a hybrid system, HYBRIDSOURCETRACKER (HST), that combines vector search and Winnowing fingerprinting to achieve scalable, high-precision provenance tracking for code generated by…

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 Synthesis Data Reversion (SDR), a method that infers the data laundering transformation used in LLM training and synthesizes queries to restore the detection signals lost when pro…

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 PACT, a provenance-aware runtime monitor that enhances agent security by tracking the origin and trust of individual tool arguments, solving the granularity mismatch in LLM agent…

This paper systematically analyzes the forensic artifacts left by popular local LLM runners (Ollama, LM Studio, llama.cpp) on Windows and Linux, providing a foundational corpus of evidence for digital…

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…

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

This paper studies six metadata-generation settings for RDF datasets and evaluates their effectiveness and faithfulness in dataset search.

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

This paper benchmarks LLMs for smart contract security analysis, concluding that while LLMs show potential, their reliability is limited by lexical bias and requires integration with traditional stati…

The paper introduces REBench, a comprehensive, standardized benchmark dataset designed to enable fair and rigorous evaluation of Large Language Models (LLMs) on complex binary reverse engineering task…

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 a novel, efficient method for checking the factuality of claims generated by LLMs by framing it as a true/false reading comprehension task and incorporating explicit test-taking str…

This paper proposes a framework to transform historical real-bug mechanisms into executable feedback targets for LLM-based unit test generation, improving real-bug detection over various baselines.

This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical sol…

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…

The paper introduces the Artificial Intelligence Bill of Materials (AIBOM) schema to provide verifiable provenance and lifecycle assurance for complex AI systems, achieving high fidelity in reproducib…