arXiv Machine Learning
Jun 17
Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation
arXiv:2606. 18190v1 Announce Type: cross Abstract: Multi-stage cyberattacks span system, network, and browser logs.
HydroJEV: A one-second, training-free screen for cyber-attack and fault attribution in water distribution networks
HydroJEV is a training‑free, one‑second model that classifies SCADA alarms in water distribution networks into cyberattack, physical fault, normal transient, or faulty sensor. In a benchmark on the C‑Town EPANET network, HydroJEV matched a hand‑written rule tree and outperformed a supervised classifier, especially when few labeled events were available, while being 20‑40 times faster than large language models. When combined with a rule tree gate, it reduced the need for human review by about a third without sacrificing accuracy.
Related stories
arXiv AI
Aug 17
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
arXiv AI
Sep 4
CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems
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.
arXiv Machine Learning
Aug 5
Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment
arXiv:2608. 02786v1 Announce Type: new Abstract: AI systems can fail silently.
arXiv AI
1d ago
Jev-IDS: System One Models for Network Intrusion Detection
JEV-IDS is an open experimental general network intrusion detection system that uses the Jev System One Model to detect zero‑day intrusions even when labeled data are scarce. The system processes one flow per request and asks the model two questions: a binary attack probability and a finite‑choice traffic category. In tests on a 300‑flow NSL‑KDD pilot split, JEV-IDS achieved an F1‑score of 0.859, precision of 0.941, recall of 0.790, and a novel‑attack recall of 0.838, while being 4.8 times faster and 3.8 times cheaper than GPT‑5.6 Luna and producing 15 times fewer false alarms than a low‑data Random Forest.
arXiv Machine Learning
Sep 7
Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection
The paper investigates how to properly validate candidate models before promoting them to replace incumbent classifiers in adaptive network intrusion detection systems. It demonstrates that promotion decisions can be biased by how challengers are constructed and the amount of evidence they receive, and that using self‑contained challenger pipelines and sufficient candidate evidence reduces apparent promotion harm. The study also shows that policy rankings shift with candidate comparability and that no single update policy dominates across benchmarks.
arXiv AI
Sep 25
Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier
The paper presents Baszta, a Polish multi‑label content‑safety classifier trained by fine‑tuning the 124M‑parameter allegro/herbert‑base‑cased model on five categories (hate, vulgarity, sexual content, crime, self‑harm) using a Focal + R‑Drop objective. In out‑of‑distribution evaluation on the Gadzi Język benchmark, Baszta achieves a small but statistically significant improvement in micro‑F1 over the Bielik Guard system, though the macro‑F1 advantage disappears when both models are properly tuned. The study also explores calibration techniques, showing that per‑category temperature scaling can recover performance lost by Platt scaling or isotonic regression, and discusses the trade‑offs between robust calibration and adversarial recall.
arXiv AI
Jul 2
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
arXiv:2508. 04064v2 Announce Type: replace-cross Abstract: Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test.
arXiv Machine Learning
Aug 18
Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection
arXiv:2608. 15761v1 Announce Type: cross Abstract: Edge-IIoTset is the reference benchmark for machine-learning intrusion detection in the industrial Internet of Things, and results reported on it cluster above 99%.
arXiv Machine Learning
Jul 31
Cybersecurity Detection Classification with Reasoning-enabled Language Models
arXiv:2607. 28460v1 Announce Type: new Abstract: A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day.
arXiv AI
Sep 1
Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation
The paper introduces a new taxonomy for benchmark contamination that categorizes leakage by the mitigation it defeats—direct, derivative, temporal, distributional, and acquired—covering both training‑time and evaluation‑time scenarios. It proposes a four‑field disclosure protocol to record contamination status alongside benchmark scores, and provides a JSON schema, validator, and examples. An empirical study of 41 documents using a pre‑registered instrument shows limited reporting of contamination types and variable reliability, highlighting gaps in current disclosure practices.
arXiv AI
Aug 18
Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
arXiv:2608. 15565v1 Announce Type: new Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known answers, which real ticket streams do not provide.