VADViT: Vision Transformer-Driven Memory Forensics for Malicious Process Detection and Explainable Threat Attribution Modern malware’s complexity challenges traditional detection and existing ML-based memory forensics, which often rely on outdated features and struggle with large-scale data. We propose VADViT, a vision transformer model that converts VAD memory regions into fused Markov, entropy, and intensity images for […]
SCsVulSegLyzer: Detecting and Extracting Vulnerable Segments from Smart Contracts Using Weakly-Supervised Learning Smart contracts (SCs) are widely used in finance but remain attractive targets for hackers due to vulnerabilities, the immaturity of Solidity, and blockchain’s immutability. We present SCsVulSegLytix, a Transformer-based model that detects and extracts vulnerable segments directly from Solidity code using only contract-level […]
Banff, Alberta, Canada (June 25-26) National Cybersecurity Consortium (NCC) conference, "Securing Canada: Evolving Threats and Innovations in Cybersecurity" and "AI-Driven Cybersecurity" Our founder and director, Prof. XYZ, was honored to serve as a panelist for two key discussions at the National Cybersecurity Consortium (NCC) Conference: “Securing Canada: Evolving Threats and Innovations in Cybersecurity” and “AI-Driven […]
Université du Québec en Outaouais (UQO) (May 28) Enhancing Cybersecurity Resilience: Advancing AI-Powered Security and Security of AI Through the UCS Knowledge Mobilization Program In this talk, we explore the evolving landscape of cybersecurity, focusing on how open-source tools and datasets drive the development of AI-powered solutions. Researchers and practitioners can leverage these resources to enhance threat detection, automate responses, […]
Hybrid attention-enhanced explainable model for encrypted traffic detection and classification Encrypted traffic detection is critical as protocols like TLS, VPNs, and Tor dominate modern networks. We propose a Hybrid Attention–LightGBM model with an augmented multi-dataset approach and Explainable AI tools (SHAP, LIME) to enhance interpretability, scalability, and generalization. Experiments show it outperforms state-of-the-art methods in […]
91ɫ U innovations advance global cybersecurity education: Through the development of innovative open-source tools and initiatives, 91ɫ’s Behaviour-Centric Cybersecurity Center (BCCC) is advancing public engagement and cybersecurity education across the globe.
Unveiling evasive malware behavior: toward generating a multi-sources benchmark dataset and evasive malware behavior profiling using network traffic and memory analysis Traditional detection methods struggle with evolving malware, and single-source datasets are no longer sufficient. We introduce BCCC-Mal-NetMem-2025, a multi-source dataset combining memory and network data, enriched with a benign behavior profiler (BUEBP) and the […]
Dalhousie University, Canada (Mar 7) Enhancing Cybersecurity Resilience: Advancing AI-Powered Security and Security of AI Through the UCS Knowledge Mobilization Program In this talk, we explore the evolving landscape of cybersecurity, focusing on how open-source tools and datasets drive the development of AI-powered solutions. Researchers and practitioners can leverage these resources to enhance threat detection, automate responses, and build more […]
Unveiling Smart Contracts Vulnerabilities: Toward Profiling Smart Contracts Vulnerabilities using Enhanced Genetic Algorithm and Generating Benchmark Dataset Smart Contracts (SCs) are critical in blockchain but remain vulnerable, with existing detection methods often lacking accuracy and scalability. We propose SCsVulLyzer V2.0, an analyzer extracting 240 features, combined with a Genetic Algorithm (GA)-based profiling method that leverages […]
Smart Contracts Vulnerability Analyzer (SCsVulLyzer-V2.0) We released the second version of the SCsVulLyzer tool as a Python open-source project to extract 240 features from Smart Contracts in Ethereum Blockchain.