Trusted AI
IBM Research is building and enabling AI solutions people can trust.
About us
Artificial intelligence systems are increasingly being used to support human decision-making. While AI holds the promise of delivering valuable insights and knowledge across a multitude of applications, broad adoption of AI systems will rely heavily on the ability to trust their output. Human trust in technology is based on our understanding of how it works and our assessment of its safety and reliability. To trust a decision made by an algorithm, we need to know that it is reliable and fair, that it can be accounted for, and that it will cause no harm. We need assurance that it cannot be tampered with and that the system itself is secure. We need to understand the rationale behind the algorithmic assessment, recommendation or outcome, and be able to interact with it, probe it – even ask questions. And we need assurance that the values and norms of our societies are also reflected in those outcomes.
Moving forward, “build for performance” will not suffice as an AI design paradigm. We must learn how to build, evaluate and monitor for trust. IBM Research AI is developing diverse approaches for how to achieve fairness, robustness, explainability, accountability, value alignment, and how to integrate them throughout the entire lifecycle of an AI application.
Watson + AI FactSheets 360
How to build trust in your AI model: the latest innovation from IBM Watson
Focus areas
As AI advances, and humans and AI systems increasingly work together, it is essential that we trust the output of these systems to inform our decisions. Alongside policy considerations and business efforts, science has a central role to play: developing and applying tools to wire AI systems for trust. IBM Research’s comprehensive strategy addresses multiple dimensions of trust to enable AI solutions that inspire confidence.
Featured work
AI Explainability 360 Toolkit
This extensible open source toolkit can help you comprehend how machine learning models predict labels by various means throughout the AI application lifecycle. Containing eight state-of-the-art algorithms for interpretable machine learning as well as metrics for explainability, it is designed to translate algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education.
AI Factsheets
IBM scientists suggest that AI services be accompanied with a factsheet outlining the details about how it operates, how it was trained and tested, its performance metrics, fairness and robustness checks, intended uses, maintenance, and other critical details.
AI Fairness 360 Toolkit
This extensible open source toolkit can help you examine, report, and mitigate discrimination and bias in machine learning models throughout the AI application lifecycle. Containing over 70 fairness metrics and 10 state-of-the-art bias mitigation algorithms developed by the research community, it is designed to translate algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education.
Adversarial Robustness 360 Toolbox
The Adversarial Robustness Toolbox is designed to support researchers and developers in creating novel defense techniques, as well as in deploying practical defenses of real-world AI systems. Researchers can use the Adversarial Robustness Toolbox to benchmark novel defenses against the state-of-the-art. For developers, the library provides interfaces which support the composition of comprehensive defense systems using individual methods as building blocks.
Publications
IBM Research AI is developing diverse approaches for how to achieve fairness, robustness, explainability, accountability, value alignment, and how to integrate them throughout the entire lifecycle of an AI application.
Please explore all of our trusting AI related research papers
| TITLE | RESEARCH AREA | VENUE | ACCESS |
|---|---|---|---|
| FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity | Transparency and Accountability | IEEE (2019) | |
| Experiences with Improving the Transparency of AI Models and Services | Transparency and Accountability | IEEE (2019) | |
| A Methodology for Creating AI FactSheets | Transparency and Accountability | IEEE (2019) | |
| AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias | Fairness | ||
| Fairness GAN: Generating Datasets with Fairness Properties using a Generative Adversarial Network | Fairness | ICLR (2019) | |
| Efficient Neural Network Robustness Certification with General Activation Functions | Robustness | NeurIPS (2018) | |
| Boolean Decision Rules via Column Generation | Explainability | NeurIPS (2018) | |
| Automated Test Generation to Detect Individual Discrimination in AI Models | Fairness | ||
| Analyzing Federated Learning through an Adversarial Lens | Robustness | ICML (2019) | |
| Interpretable Multi-Objective Reinforcement Learning through Policy Orchestrations | Value Alignment | ICML (2019) | |
| Data Pre-Processing for Discrimination Prevention: Information-Theoretic Optimization and Analysis | Fairness | ||
| Evolutionary Search for Adversarially Robust Neural Networks | Robustness | ICLR (2019) | |
| Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction | Fairness |
Try our tech
At IBM Research, we create innovative tools and resources to help unleash the power of AI. See for yourself. Take our tech for a spin.
Open Source and Tools
AI FactSheets 360
The AI FactSheets 360 project was built to foster trust in AI by increasing transparency. We set out to offer an increased understanding of how an AI model was created and deployed and built the tools you need to govern this creation process.
Tame any bias lurking in AI models
Bias occurs in data used to train a model. We have provided three sample datasets that you can use to explore bias checking and mitigation. Each dataset contains attributes that should be protected to avoid bias.
Explain AI decisions
AI Explainability 360 offers a collection of algorithms that provide diverse ways of explaining decisions generated by machine learning models.
Latest news and blog
Discover the latest news and research from the IBM Research Trusting AI.
IBM FactSheets Further Advances Trust in AI
Michael Hind| July 9, 2020
Introducing AI Explainability 360
Aleksandra Mojsilovic| August 8, 2019
Factsheets for AI Services
Pin-Yu Chen and Sijia Liu | August 2, 2019
IBM Science for Social Good 2019 Projects Announced
Kush R. Varshney and Aleksandra Mojsilovic | July 23, 2019
IBM Research AI Advancing, Trusting, and Scaling Learning at ICLR
John R. Smith | May 2, 2019
Efficient Adversarial Robustness Evaluation of AI Models with Limited Access
Pin-Yu Chen and Sijia Liu | January 30, 2019
Building Ethically Aligned AI
Francesca Rossi | January 23, 2019
‘Show and Tell’ Helps AI Agent Align with Societal Values
Kush Varshney | October 25, 2018
Trust and Transparency for AI on the IBM Cloud
Kush Varshney | September 19, 2018
Introducing AI Fairness 360
Kush Varshney | September 19, 2018
Factsheets for AI Services
Aleksandra Mojsilovic |August 22, 2018
The Adversarial Robustness Toolbox v0.3.0: Closing the Backdoor in AI Security
Irina Nicolae and Mathieu Sinn | August 22, 2018
Science for Social Good
Applied science can help solve the world’s toughest problems and inspire business innovation. IBM Research and its partners are applying artificial intelligence, cloud and deep science to scale social impact.