Kevin Eykholt

Michael V. Le

Salman Ahmed

Dan Williams

Hani Jamjoom

Julian Stephen

Shriti Priya

Taesung Lee

Mike Murphy

Kim Martineau

News

Research

Technical note

Saška Mojsilović wants to channel AI for good. She may also make you rethink sour cabbage

AI diffusion models can be tricked into generating manipulated images

Protect yourself from bad neighbors in the cloud

Simplifying cloud security policies with AI

An open-source toolkit for debugging AI models of all data types

An AI model trained on data that looks real but won’t leak personal information

DARPA and IBM are ensuring that anyone can protect their AI systems from hackers

W're developing capabilities to secure the data-AI lifecycle. We adopt a Zero Trust paradigm with innovation to discover, protect and monitor sensitive data.

Data and AI Security

IBM Solution: IBM Cloud Pak for Data

NDSS 2025

HPCA 2025

ICISSP 2025

ICLR 2025

NAACL 2025

Fairness, Accountability, Transparency

AI Privacy

Adversarial Robustness and Privacy

AI Transparency

Foundation Models

Machine Learning

Generative AI

Security

Cloud Security

Finance

Explainable AI

AI Testing

Even advanced AI systems can be vulnerable to adversarial attacks. We’re making tools to protect AI and certify its robustness, including quantifying the vulnerability of neural networks and designing new attacks to make better defenses. And we’re helping AI systems adhere to privacy requirements.

We’re making tools to protect AI and certify its robustness, and helping AI systems adhere to privacy requirements.

We’re working on building the most secure cloud infrastructure platforms. Our research focuses on ensuring the integrity of everything in the stack, reducing the attack surface of cloud systems, and advancing the use of confidential computing and hardware security modules.

Advancing the system integrity of cloud systems in mission-critical situations.

As organizations move to the hybrid cloud, they must protect sensitive data and comply with regulations that allow them to take advantage of AI. We’re designing systems to monitor and protect data, building trust in AI through robust evaluation, certification, and hardening against attacks.

The future of computing lies in the hybrid cloud. We're creating a hybrid data fabric that provides secure,  governed data access from anywhere, enables self-service discovery of the right data at the right time, and takes a holistic view at minimizing total cost of ownership for AI and analytics.

Data Management

The hybrid cloud can help businesses tap into the potential of the cloud, while retaining the benefits of private environments. At IBM Research, we’re pursuing open-source standards and code to create an agile and scalable platform that can be deployed anywhere.

Hybrid Cloud Platform

Saška Mojsilović at IBM Research in Yorktown

Data and AI Security

Our work

DARPA and IBM are ensuring that anyone can protect their AI systems from hackers

An AI model trained on data that looks real but won’t leak personal information

An open-source toolkit for debugging AI models of all data types

Simplifying cloud security policies with AI

Protect yourself from bad neighbors in the cloud

AI diffusion models can be tricked into generating manipulated images

Publications

Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case Study

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging

Workshop on Data Integrity and Secure Cloud Computing (DISCC)

Quantifying the Bit-Error Resilience of FHE Compute

Automated Expansion of Privacy Data Taxonomy for Compliant Data Breach Notification

Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation

IBM Solution: IBM Cloud Pak for Data

Related topics