Managing the risk in AI: Spotting the “unknown unknowns”ResearchOrna Raz, Sam Ackerman, and Marcel Zalmanovici06 Jun 20215 minute readAIAI Testing
AI boosts the discovery of metamaterials vital for next-gen gadgetsResearchYoussef Mroueh, Karthikeyan Shanmugam, and Payel Das20 May 202110 minute readAIMaterials DiscoveryTrustworthy GenerationUncertainty Quantification
New research helps make AI fairer in decision-makingResearchMikhail Yurochkin and Yuekai Sun07 May 20215 minute readAIFairness, Accountability, TransparencyTrustworthy AI
IBM researchers investigate ways to help reduce bias in healthcare AIResearchYoonyoung Park15 Apr 20216 minute readAIFairness, Accountability, TransparencyHealthcareImpact ScienceResponsible TechnologyTrustworthy AI
IBM AI finds new peptides – paving the way to better drug designResearchAleksandra Mojsilovic and Payel Das11 Mar 20214 minute readAccelerated DiscoveryAIGenerative AIMaterials DiscoveryTrustworthy Generation
IBM researchers check AI bias with counterfactual textResearchInkit Padhi, Nishtha Madaan, Naveen Panwar, and Diptikalyan Saha05 Feb 20215 minute readAI TestingFairness, Accountability, Transparency
AI goes anonymous during training to boost privacy protectionReleaseAbigail Goldsteen26 Jan 20214 minute readAdversarial Robustness and PrivacyData and AI SecurityMachine LearningSecurity
Preparing deep learning for the real world – on a wide scaleResearchPin-Yu Chen15 Dec 20203 minute readAdversarial Robustness and PrivacyAIMachine LearningTrustworthy AI
DualTKB: A Dual Learning Bridge between Text and Knowledge BaseResearchPierre Dognin13 Nov 20206 minute readKnowledge and ReasoningNatural Language ProcessingTrustworthy Generation
Adversarial Robustness Toolbox: One Year Later with v1.4ReleaseAbigail Goldsteen and Beat Buesser02 Oct 20204 minute readAdversarial Robustness and PrivacyData and AI SecurityMachine LearningSecurity
Image captioning as an assistive technologyNewsYoussef Mroueh23 Jul 20205 minute readComputer VisionTrustworthy AITrustworthy Generation
IBM FactSheets Further Advances Trust in AIReleaseMichael Hind09 Jul 20204 minute readFairness, Accountability, TransparencyHuman-Centered AITrustworthy AI
IBM Differential Privacy Library: The single line of code that can protect your dataReleaseNaoise Holohan26 Jun 20202 minute readAdversarial Robustness and PrivacyData and AI SecuritySecurity
Characterizing the evolution of tasks within occupationsResearchMartin Fleming and Subhro Das23 Feb 20204 minute readFuture of WorkTrustworthy AI
IBM joins Stanford Human-Centered AI Institute’s partner programNewsJeff Welser14 Nov 2019Human-Centered AINatural Language ProcessingTrustworthy AI
Introducing AI Explainability 360ReleaseAleksandra Mojsilovic08 Aug 2019AIAI TransparencyExplainable AI