Awesome Adversarial Deep Learning
A curated collection of resources on adversarial examples in deep learning, covering attacks, defenses, and applications.
What is Awesome Adversarial Deep Learning?
Awesome Adversarial Examples for Deep Learning is a curated GitHub repository that aggregates academic papers, tools, and resources related to adversarial attacks and defenses in deep learning. It addresses the growing need for organized reference material in the field of AI security, where adversarial examples—inputs designed to fool machine learning models—pose significant robustness challenges. The collection spans foundational research, attack methodologies, defensive strategies, and real-world applications across various domains.
Machine learning researchers, AI security specialists, and graduate students focusing on adversarial robustness, model security, or trustworthy AI. It's particularly valuable for those conducting literature reviews or developing new defense mechanisms against adversarial attacks.
Unlike scattered academic databases, this project offers a centralized, thematically organized resource list specifically for adversarial machine learning. It saves researchers time by curating high-impact papers and tools, and it's community-maintained to stay current with rapid advancements in the field.
Overview
A curated list of awesome resources for adversarial examples in deep learning
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
