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…

This paper systematically evaluates Provenance-based Intrusion Detection Systems (PIDSes) in real industrial scenarios, revealing that existing systems struggle with data heterogeneity, advanced attac…

The paper introduces Auto-Prov, an end-to-end framework that uses Large Language Models (LLMs) to automatically construct functional-embedded provenance graphs from diverse logs, enhancing anomaly det…

ProHunter is an efficient and accurate system that uses whole-system provenance graphs to proactively hunt for Advanced Persistent Threats (APTs), outperforming existing methods in both efficiency and…

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…

ZERO-APT introduces a novel closed-loop adversarial framework for automated penetration testing that simulates attacks against an intelligent, real-time defending system, achieving a high attack succe…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that simpler, shallower Deep Neural Network architectures with reduced features and ReLU activations can inherently improve the robustness of ML-NIDS against gradient-based adve…

This Survey of Knowledge (SoK) identifies a disconnect between academic NIDS research and real-world operational contexts, proposing foundational changes to reshape future research.

The paper argues that zero-day attacks primarily exploit undisclosed vulnerabilities rather than exhibiting novel behaviors, advocating for vulnerability-centric detection methods over purely behavior…

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…

MA-IDS proposes a Multi-Agent RAG framework that uses LLMs and a self-building Experience Library to achieve explainable and self-improving intrusion detection for resource-constrained IoT networks.

ML Defender (aRGus NDR) is an open-source, embedded Machine Learning Network Intrusion Detection System (NIDS) that achieves superior detection rates for botnet and anomalous traffic on resource-const…

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

The paper introduces Trace, a forensic framework that fingerprints the model family of autonomous AI attack agents using terminal behavior, enabling subsequent prompt injection to extract system promp…

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

The paper introduces an end-to-end framework that not only detects network intrusions using deep learning but also generates actionable, citation-grounded mitigation reports using a Retrieval-Augmente…

The paper introduces HIDBench, a new benchmark for evaluating LLMs' ability to perform host-based intrusion detection using complex, noisy system logs, finding that model performance degrades signific…

The paper evaluates AI's effectiveness in detecting network intrusions and cryptographic side-channel leakage, finding high accuracy in stable environments but performance degradation with novel traff…