International Journal of Adversarial Machine Learning and Robust Artificial Intelligence

Editorial Team Current Archives Author Guidelines Editor Guidelines Login Register

About Us

Published twice a year by MAT Journals Pvt. Ltd., the International Journal of Adversarial Machine Learning and Robust Artificial Intelligence provides a platform for research on secure, reliable, and robust AI systems. Its scope includes adversarial attacks and defenses, robust machine learning, AI safety, trustworthy AI, privacy-preserving techniques, explainable AI, model robustness, and related applications. The journal welcomes innovative work focused on developing resilient and dependable intelligent systems capable of functioning effectively in challenging and adversarial environments.

Aim

The journal is dedicated to advancing research in robust, secure, and dependable artificial intelligence, with emphasis on adversarial machine learning, AI security, privacy, and model resilience. It provides a platform for developing trustworthy and resilient intelligent systems capable of maintaining reliable performance in adversarial, uncertain, and evolving environments.

Focus and Scope

Adversarial Machine Learning and Adversarial Attacks Robust and Secure Artificial Intelligence Adversarial Defense and Model Hardening Robust Machine Learning and Deep Learning AI Security, Privacy, and Threat Detection Trustworthy, Explainable, and Responsible AI Adversarial Examples and Robustness Evaluation Data Poisoning, Model Evasion, and Model Extraction

Secure Neural Networks and AI Architectures Anomaly Detection and Intelligent Threat Analysis Privacy-Preserving Machine Learning Federated and Distributed Learning Security Robust Computer Vision and Natural Language Processing AI Security for IoT, Edge, and Autonomous Systems AI Risk Assessment, Verification, and Validation Emerging Trends in Adversarial Learning and Robust AI