Adversarial Game
Adversarial games model interactions between competing agents, aiming to understand strategic decision-making under opposition. Current research focuses on applying this framework to diverse areas, including robotics, cybersecurity, and machine learning, often employing game-theoretic formulations and algorithms like reinforcement learning and generative adversarial networks (GANs) to analyze optimal strategies and model vulnerabilities. These studies are significant for improving the robustness and fairness of AI systems, enhancing security protocols, and providing insights into complex real-world scenarios involving competing interests.
Papers
Scalable Adversarial Online Continual Learning
Tanmoy Dam, Mahardhika Pratama, MD Meftahul Ferdaus, Sreenatha Anavatti, Hussein Abbas
Latent Preserving Generative Adversarial Network for Imbalance classification
Tanmoy Dam, Md Meftahul Ferdaus, Mahardhika Pratama, Sreenatha G. Anavatti, Senthilnath Jayavelu, Hussein A. Abbass