This repository is a curated list of resources focused on AI security, specifically covering adversarial attacks and defenses in machine learning. It serves as a comprehensive reference for researchers, security professionals, and developers interested in understanding and mitigating vulnerabilities in AI systems.

How It Works

The list categorizes resources into types such as research papers, slides, videos, blog posts, and code. It further organizes these by attack vectors like adversarial examples, evasion attacks, poisoning attacks, and feature selection, providing a structured overview of the AI security landscape.

Highlighted Details

• Extensive collection of research papers on adversarial examples, evasion, and poisoning attacks.
• Includes links to practical code libraries like CleverHans and Foolbox for benchmarking and generating adversarial examples.
• Covers a wide range of AI applications, including computer vision, speech recognition, and malware classification.
• Features resources on both offensive techniques and defensive strategies.

Maintenance & Community

This is a community-driven "awesome" list, indicating it's maintained by contributions from the open-source community. Specific contributors or community channels are not detailed in the README.

Licensing & Compatibility

The repository itself, as a collection of links and curated content, does not appear to have a specific license. However, the linked resources may have their own licenses. Compatibility for commercial use would depend on the licenses of the individual linked projects and papers.

Limitations & Caveats

This is a curated list and not a software project with executable code. The quality and applicability of the resources depend on the original sources. The list may not be exhaustive and is subject to the curation choices of its maintainers.