About
Research & Development
Ensuring Equitable AI Protection: The Sy-FAR Method
TLDR: Sy-FAR is a new technique that improves the fairness of machine learning systems against adversarial attacks by promoting "symmetry" in misclassification patterns. Instead...
Research & Development
FusionMAE: A New AI Model for Streamlining Fusion Plasma Control
TLDR: FusionMAE is a large-scale AI model that uses a masked autoencoder to compress 88 diagnostic signals from fusion plasmas into a unified "embedding."...
Research & Development
ODiSAR: Digital Twins for Proactive Anomaly Detection in Self-Adaptive Robots
TLDR: ODiSAR is a novel approach using AI-powered digital twins to proactively detect out-of-distribution (OOD) behaviors in self-adaptive robots (SARs). It employs a Transformer-based...
Research & Development
Enhancing Smart Contract Security: A Hybrid Approach to Defect Validation
TLDR: This research introduces a three-stage pipeline to improve smart contract vulnerability detection by reducing false alarms. It combines Slither-based static analysis, Large Language...
Research & Development
GView: A Unified Framework for Advanced Binary Forensics with AI Integration
TLDR: GView is an innovative open-source framework designed to simplify and enhance cybersecurity forensic analysis. It combines visual, semantic, and AI-enhanced reasoning to overcome...
Research & Development
TFANet: Improving Referring Image Segmentation in Complex Visual Scenes
TLDR: TFANet is a novel three-stage network for Referring Image Segmentation (RIS) that enhances accuracy by systematically aligning image and text features. It introduces...