Artificial intelligence systems have become increasingly prevalent in everyday life and enterprise settings, and they’re now often being used to support human decision-making. These systems have grown increasingly complex and efficient, and AI holds the promise of uncovering valuable insights across a wide range of applications. But broad adoption of AI systems will require humans to trust their output. When people understand how technology works, and we can assess that it’s safe and reliable, we’re far more inclined to trust it. Many AI systems to date have been black boxes, where data is fed in and results come out. To trust a decision made by an algorithm, we need to know that it is fair, that it’s reliable and can be accounted for, and that it will cause no harm. We need assurances that AI cannot be tampered with and that the system itself is secure. We need to be able to look inside AI systems, to understand the rationale behind the algorithmic outcome, and even ask it questions as to how it came to its decision. At IBM Research, we’re working on a range of approaches to ensure that AI systems built in the future are fair, robust, explainable, account, and align with the values of the society they’re designed for. We’re ensuring that in the future, AI applications are as fair as they are efficient across their entire lifecycle. Bringing a common language to AI evaluation News Kim Martineau 23 Jul 2026 AI AI Transparency Fairness, Accountability, Transparency Generative AI Bringing a common language to AI evaluation AI Transparency Fairness, Accountability, Transparency How the wrong training environment can teach AI models to misbehave Research Peter Hess 09 Jul 2026 AI AI Planning Explainable AI Generative AI How the wrong training environment can teach AI models to misbehave Introducing the IBM Granite 4.1 family of models Release Mike Murphy 29 Apr 2026 AI Computer Vision Foundation Models Generative AI Speech Trustworthy AI Introducing the IBM Granite 4.1 family of models Computer Vision Foundation Models Toward a transparent supply chain for AI News Kim Martineau 26 Mar 2026 AI AI Transparency Data and AI Security Toward a transparent supply chain for AI AI Transparency Data and AI Security How IBM Granite became a leader in responsible AI Explainer Kim Martineau 13 Feb 2026 AI Generative AI Trustworthy AI Trustworthy Generation How IBM Granite became a leader in responsible AI Trustworthy Generation LLMs have model cards. Now, benchmarks do, too Release Kim Martineau 16 Dec 2025 AI Fairness, Accountability, Transparency Generative AI Trustworthy AI LLMs have model cards. Now, benchmarks do, too Fairness, Accountability, Transparency See more of our work on Trustworthy AI AI Testing We’re designing tools to help ensure that AI systems are trustworthy, reliable and can optimize business processes. Adversarial Robustness and Privacy We’re making tools to protect AI and certify its robustness, and helping AI systems adhere to privacy requirements. Adversarial Robustness and Privacy Explainable AI We’re creating tools to help AI systems explain why they made the decisions they did.

Fairness, Accountability, Transparency We’re developing technologies to increase the end-to-end transparency and fairness of AI systems. Fairness, Accountability, Transparency Trustworthy Generation We’re developing theoretical and algorithmic frameworks for generative AI to accelerate future scientific discoveries. Trustworthy Generation Uncertainty Quantification We’re developing ways for AI to communicate when it's unsure of a decision across the AI application development lifecycle. Uncertainty Quantification Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting Zhi-yi Chin Pin-Yu Chen et al. 2026 COLM 2026 Conference paper Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting Zhi-yi Chin Pin-Yu Chen et al. From Alignment to Access Control: A Unified View of GenAI Policy Enforcement Nathalie Baracaldo Angel 2026 USENIX Security 2026 Talk From Alignment to Access Control: A Unified View of GenAI Policy Enforcement Nathalie Baracaldo Angel Nathalie Baracaldo Angel USENIX Security 2026 The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search Rongzhe Wei Peizhi Niu et al. 2026 ICML 2026 Conference paper The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search Rongzhe Wei Peizhi Niu et al. ProbeLLM: Automating Principled Diagnosis of LLM Failures Yue Huang Zhengzhe Jiang et al. 2026 ICML 2026 Conference paper ProbeLLM: Automating Principled Diagnosis of LLM Failures Yue Huang Zhengzhe Jiang et al. Position: Agentic Systems Should be General Elron Bandel Asaf Yehudai et al. 2026 ICML 2026 Conference paper Position: Agentic Systems Should be General Elron Bandel Asaf Yehudai et al. Scaling Laws in Model Fine-tuning for Audio DeepFake Detection Xiang Li Pin-Yu Chen et al. 2026 ICML 2026 Conference paper Scaling Laws in Model Fine-tuning for Audio DeepFake Detection Xiang Li Pin-Yu Chen et al. Building trustworthy AI with Watson Our research is regularly integrated into Watson solutions to make IBM’s AI for business more transparent, explainable, robust, private, and fair.