LF AI & Data Foundation Announces Graduation of ART

The LF AI & Data Foundation, the organization building an ecosystem to sustain open source innovation in artificial intelligence (AI) and data open source projects, is announcing today that the hosted project Adversarial Robustness Toolbox (ART) is advancing from an Incubation level project to a Graduate level. This graduation is the result of ART demonstrating thriving adoption, an ongoing flow of contributions from multiple organizations, and both documented and structured open governance processes. ART has also achieved an OpenSSF Best Practices Badge, and demonstrated a strong commitment to its community of users and contributors. 

ART provides tools that enable developers and researchers to evaluate, defend, certify and verify the robustness, security and privacy of Machine Learning models against the adversarial threats of evasion, poisoning, extraction, and inference to enable trustworthy AI. ART supports all popular machine learning frameworks including TensorFlow, PyTorch, Keras, MXNet, scikit-learn, XGBoost, and many more. ART also facilitates research in adversarial machine learning by providing reference implementations of attack and defense algorithms and a comprehensive set of notebooks and example scripts on adversarial machine learning applications.

Created and open-sourced by IBM in 2018, ART joined LF AI & Data as an Incubation project in June 2020. As an Incubation project, the project has benefited from the LF AI & Data’s various enablement services to foster its growth and adoption; including program management support, event coordination, legal services, and marketing services ranging from website creation to project promotion. 

“ART is a great example of a project that grew significantly as an LF AI & Data hosted project and benefited from a range of provided services and collaboration opportunities. The project’s graduation is a sign of maturity, functioning open governance, large-scale adoption, and significant integration efforts with other projects in the ecosystem. ART meets our graduation criteria and we’re proud to be its host Foundation. As a Graduate project, we will continue to support it via an extended set of services tailored for Graduated projects. We’re also excited that the project is now eligible for a voting seat on LF AI & Data’s Technical Advisory Council. Congratulations, ART! ” 

•  Dr. Ibrahim Haddad, Executive Director of the LF AI & Data. 

“The growth and development of ART’s contributors community is particularly impressive. As a co-chair of LFAI Trusted AI Committee, where I frequently interact with ART contributors and adopters, from IBM, DARPA, Two Six Technologies, Kyushu University, Intel, University of Chicago, MITRE, General Motors, Microsoft, AGH University of Science and Technology, Rensselaer Polytechnic Institute (RPI), IMT Atlantique, Johns Hopkins University, Troj.AI and others, ART is on an impressive trajectory!”

• Animesh Singh, CTO and Director, Watson AI and Data Open Technology

“Leading the development of ART and being part of its team of amazing open-source contributors and colleagues around the world commited to create trustworthy AI has been an incredible experience so far. LFAI has been a great supporter, mentor, and accelerator for ART and has significantly contributed to growing ART and its global and active user community. Being recognized and honored with the Graduate level is an incredible achievement for the entire ART team and it is an honor to become a member of LF AI & Data’s Technical Advisory Council to represent ART.” 

• Dr. Beat Buesser, Research Staff Member in AI Security & Privacy at IBM Research and Project Leader of ART. 

“Security is a team sport and everyone wins when tools to make AI systems secure are democratized. The Adversarial Robustness Toolbox (ART) is an important step in this direction for the community. Counterfit, Microsoft’s open source toolkit that empowers security professionals and engineers to seamlessly assess the security posture of AI systems, builds on the strong foundation of open source adversarial ML frameworks like ART.  Congratulations to ART for being recognized as a mature graduate of LF AI & Data Foundation.”

• Hyrum Anderson, Principal Architect, Microsoft Azure Trustworthy Machine Learning

“Business organizations and governments are increasingly relying on AI to make critical, life-changing decisions without following due process to determine where their models are at risk. As the call for responsible AI grows louder, it is so incredibly important to have a project like ART continue building in public to bridge the gap between research and practical use for everyone to see and benefit from. Congratulations to the ART team, and thank you for helping us all reduce AI Risk!”

• Stan Petley, Director of Engineering, TrojAI Inc.