ThreatDetect

ThreatDetect ThreatDetect is a Streamlit-based insider threat detection prototype that analyzes employee activity data and flags potentially risky behavior. It uses a trained XGBoost classifier together with an Isolation Forest anomaly detector to produce organisation-level risk summaries and...

Securing Agentic Commerce through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment Authorization

The growing use of autonomous artificial intelligence agents in digital commerce creates new security concerns involving agent impersonation, unauthorized payments, compromised agents, and misuse of delegated authority. This research introduces the Autonomous Commerce Agent Guard System ACAGS, a...

Systematically Optimized CNN-Transformer with Focal Loss for Imbalanced Intrusion Detection on NSL-KDD

Intrusion Detection Systems IDS struggle with imbalanced datasets like NSL-KDD, especially in detecting rare R2L and U2R attacks. This work describes a systematically optimized and explainable framework using a CNN-Transformer architecture to improve performance on highly imbalanced data. We...

CVE-2026-92786

A flaw was found in LightGBM. The software does not properly validate data within text models, which can be exploited by an attacker. By crafting a malicious model file, an attacker can trigger an out-of-bounds write during the SHAP prediction process. This vulnerability could lead to arbitrary...

Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection

Large language models LLMs are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation through prompt injection and jailbreak attacks. Classifier-based guardrails, such as Prompt Guard 2, are widely used as a first line of defense against suc...

CVE-2026-92786

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

CVE-2026-92786 LightGBM through 4.7.0 Out-of-Bounds Write via Crafted Model

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

CVE-2026-92786 LightGBM through 4.7.0 Out-of-Bounds Write via Crafted Model

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

CVE-2026-92786 LightGBM through 4.7.0 Out-of-Bounds Write via Crafted Model

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

CVE-2026-92786

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

EUVD-2026-81049

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

CVE-2026-92786

LightGBM versions through 4.7.0 are affected by an out-of-bounds write vulnerability triggered during SHAP prediction (feature contribution computation). The root cause is a failure to validate child and split array values when parsing text model files. An attacker can craft a malicious model fil...

CVE-2026-92786: Out-of-bounds Write

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen...

PT-2026-94063

Name of the Vulnerable Software and Affected Versions LightGBM versions prior to 4.7.1 Description Failure to validate child and split array values when parsing text models allows for out-of-bounds memory writes during SHAP SHapley Additive exPlanations, a method used to explain the output of...

Self-Verifying Anomaly Detection Using Explainable AI for Cybersecurity of DER Networks

The rapid growth of Distributed Energy Resources DERs has significantly expanded the cyber attack surface of modern power grids. Furthermore, increasing sophistication in attack techniques demands anomaly detection systems ADS that are accurate, interpretable, and reliable to support DER...

A Calibrated and Explainable Bimodal Machine Learning Framework for Hybrid Intrusion Detection

Modern communication systems face critical gaps in detecting unknown attacks and rare threat classes due to extreme data imbalance and black-box decision logic. We propose a bimodal framework of calibrated and explainable machine learning ML for network security, unifying known-class precision wi...

Dueling Deep Q-Learning for Intrusion Detection

Intrusion detection systems IDS and automated systems for detecting and reporting cyber threats, are commonly handled via supervised machine learning methods. Though effective, these models struggle to effectively adapt to new attack types. This study proposes a novel approach by employing a...

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate ASR, yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluat...

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior MLP conference study to Random Forest and XGBoost across four tabular securi...

Multi-Level Distributional Entropy for Explainable Network Intrusion Detection

Machine learning network intrusion detection systems IDS rely on aggregate flow statistics that discard distributional structure, while established entropy measures require raw packet sequences unavailable in pre-aggregated flow datasets. We propose Multi-Level Distributional Entropy MDE, an...