Toward a transparent supply chain for AI
News
Kim Martineau
Data and AI Security
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.
Our work
IBM further strengthens Granite for enterprise deployment with HackerOne
NewsMike MurphyDARPA and IBM are ensuring that anyone can protect their AI systems from hackers
NewsMike MurphyAn AI model trained on data that looks real but won’t leak personal information
ResearchKim MartineauAn open-source toolkit for debugging AI models of all data types
Technical noteKevin Eykholt and Taesung LeeSimplifying cloud security policies with AI
Technical noteJulian Stephen and Shriti Priya- See more of our work on Data and AI Security
Publications
Position: Mind the Gap-Closing the Growing Disconnect Between Vulnerability Disclosure and AI Security
- Lukas Bieringer
- Sean Mcgregor
- et al.
- 2026
- IEEE SaTML 2026
PaperWhen an Agent Acts on Your Behalf, Who Holds the Keys?
- Mariusz Sabath
- Maia Iyer
- 2026
- KubeCon EU 2026
Talk4th Workshop on Data Integrity and Secure Cloud Computing (DISCC)
- Pradip Bose
- Jennifer Dworak
- et al.
- 2026
- HPCA 2026
WorkshopPreventing Multimodal Cross-Domain Resource Abuse in MCP Tools
- Shriti Priya
- Teryl Taylor
- 2025
- ACSAC 2025
TalkWhen Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
- Aladin Djuhera
- Farhan Ahmed
- et al.
- 2025
- NeurIPS 2025
Workshop paperUnclonable fluorescent tags produced on bioplastics by in-situ electron beam irradiation
- S. Calderon V
- L.F. Ballesteros
- et al.
- 2025
- Mater. Today Nano
Paper
IBM Solution: IBM Cloud Pak for Data
Our research is regularly incorporated into new security features for IBM Cloud Pak for Data.
Learn more