As real-world AI deployments increase, IBM says the contributions can help ensure they're fair, secure and trustworthy. IBM on Monday announced it's donating a series of open-source toolkits designed to help build trusted AI to a Linux Foundation project, the LF AI Foundation. As real-world AI deployments increase, IBM says the contributions can help ensure they're fair, secure and trustworthy. "Donation of these projects to LFAI will further the mission of creating responsible AI-powered technologies and enable the larger community to come forward and co-create these tools under the governance of Linux Foundation," IBM said in a blog post, penned by Todd Moore, Sriram Raghavan and Aleksandra Mojsilovic. Specifically, IBM is contributing the AI Fairness 360 Toolkit, the Adversarial Robustness 360 Toolbox and the AI Explainability 360 Toolkit.

Next week at AI Research Week, hosted by the MIT-IBM Watson AI Lab in Cambridge, MA, we will publish the first major release of the Adversarial Robustness 360 Toolbox (ART). Initially released in April 2018, ART is an open-source library for adversarial machine learning that provides researchers and developers with state-of-the-art tools to defend and verify AI models against adversarial attacks. ART v1.0 marks a milestone in AI security, introducing new features that extend ART to conventional machine learning models and a variety of data types beyond images: The number of reports on real-world exploitations using adversarial attacks against AI is growing, as in the case of anti-virus software, highlighting the importance of understanding, improving and monitoring the adversarial robustness of AI models. ART provides a comprehensive and growing set of tools to systematically assess and improve the robustness of AI models against adversarial attacks, including evasion and poisoning. In evasion attacks, the adversary crafts small changes to the original input to an AI model in order to influence its behaviour.