Adversarial Learning
Adversarial learning is a machine learning technique that improves model robustness and fairness by pitting two neural networks against each other—a generator and a discriminator—in a competitive training process. Current research focuses on applications across diverse fields, including improving fairness in predictive analytics, enhancing robustness in reinforcement learning and domain adaptation, and mitigating the effects of adversarial attacks on various models. This approach is significant because it addresses critical limitations of standard machine learning methods, leading to more reliable and equitable outcomes in various applications, from financial risk assessment to medical image analysis and autonomous systems.
Papers
CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks
Munsif Ali, Leonardo Rossi, Massimo Bertozzi
Adversarial Inception for Bounded Backdoor Poisoning in Deep Reinforcement Learning
Ethan Rathbun, Christopher Amato, Alina Oprea
Diffusing States and Matching Scores: A New Framework for Imitation Learning
Runzhe Wu, Yiding Chen, Gokul Swamy, Kianté Brantley, Wen Sun
DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis
Yu Gu, Qiushi Zhu, Guangzhi Lei, Chao Weng, Dan Su
Adversarial Neural Networks in Medical Imaging Advancements and Challenges in Semantic Segmentation
Houze Liu, Bo Zhang, Yanlin Xiang, Yuxiang Hu, Aoran Shen, Yang Lin
DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks
Zohreh Aghababaeyan, Manel Abdellatif, Lionel Briand, Ramesh S
Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
Kevin Eykholt, Farhan Ahmed, Pratik Vaishnavi, Amir Rahmati