The paper audits the reproducibility of knowledge‑graph extraction from threat reports by re‑implementing matching rules for only five of twelve systems and re‑scoring ten system outputs under eight protocols. The audit shows that different matching protocols can reverse most pairwise system rankings and that a fixed prediction set can vary from 0.16 to 0.70 F1. The authors also build CTIForge to isolate validation effects, finding that validation changes precision across backbones and increases entity‑type disputes, and they release the full pipeline, protocol suite, and audit records.
arXiv:2607. 24563v1 Announce Type: new Abstract: Security Operations Centers increasingly rely on automated mapping of Cyber Threat Intelligence reports to MITRE ATT&CK, yet extractor outputs remain fallible and are often stored without the evidence, provenance, and validation history needed to decide whether an individual mapping should be trusted.
The paper evaluates CASCADE, a fully local layered defense for Model Context Protocol (MCP)-based systems, by conducting a component ablation and corpus audit on a fixed 5,000-sample dataset. It demonstrates that the choice of aggregation convention heavily influences reported metrics, that detection performance varies with provenance, and that the released configuration does not fully disclose the operating point. The study also shows that a local review model invoked for a third of requests does not alter classification outcomes, highlighting the importance of reproducibility and transparency in defense evaluations.
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
arXiv:2608.28394v1 Announce Type: cross Abstract: Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneit...
arXiv:2610.20417v1 Announce Type: new Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures a...
TriShieldRAG introduces a three‑layered defense for Retrieval‑Augmented Generation: an Ingest Guard that screens documents, a Retrieval Scorer that re‑ranks based on trust, and a Cross‑LLM Consensus that validates evidence across three models. Against the original PoisonedRAG attack on the 2.68M‑passage Natural Questions corpus, the framework reduces attack success from about 79% to 1%. However, adaptive attacks that only alter document formatting can bypass the Ingest Guard and still achieve high success rates, revealing limits of layered defenses that rely on the same retrieved evidence.
JudgeStealer is a query‑efficient framework that extracts the judging capabilities of large language models across pointwise scoring, pairwise comparison, and listwise ranking protocols. It leverages cross‑protocol agreement to convert pointwise scores into higher‑order supervision, dynamically selects informative inputs, and applies score smoothing and multi‑protocol review to preserve ordinal structure and avoid catastrophic forgetting. Experiments show it outperforms existing baselines, achieving up to 73.3% accuracy on pointwise, 87.0% on pairwise, and 71.6% on listwise evaluation, while remaining robust against common extraction defenses.
The paper introduces concept provenance, a framework that categorizes query concepts into backstory-supported, human-central, human-tail, and candidate answer-side zones to detect knowledge intrusion in LLM-generated search queries. Applying this framework to 77,004 queries across 100 topics, 8 LLMs, and 5 prompt conditions, the authors find that 7.40% of non-generic concepts are candidate answer-side and appear in 97 of 100 topics, with human validation revealing 68.2% relaxed precision and equal contributions from knowledge and deployment intrusion. The study shows that while prompt conditions do not eliminate intrusion, post-generation concept-provenance selection can achieve 99% elimination, positioning concept provenance as a diagnostic tool rather than an evaluation predictor.
arXiv:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and int...
The paper introduces AHLERT, a system that automatically extracts environment-aware hunt leads from Cyber Threat Intelligence reports. It combines a hybrid retriever—dense vector search plus multi-hop knowledge‑graph traversal seeded with MITRE ATT&CK—with ontology‑grounded retrieval‑augmented generation to constrain leads to a defender’s assets. Evaluations on public CTI reports show that AHLERT doubles mean F1 scores and achieves an effectiveness score of ~86.95% compared to off‑the‑shelf LLM models.
The paper introduces a claim‑anchored execution contract that binds a tool‑using agent’s emitted claim to its exact source span, the ordered execution prefix that produced it, and the source version and access state observed. Each receipt contains deterministic anchors, source identifiers, offsets, hashes, quotes, and a domain‑separated execution commitment, allowing a verifier to reconstruct these bindings before semantic or task labels are joined. The contract defines seven independently testable properties and demonstrates high detection rates against cross‑object attacks, with strong performance on conflict‑aware support guard evaluations.
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.