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
Saška Mojsilović wants to channel AI for good. She may also make you rethink sour cabbage
NewsWhat is synthetic data?
ExplainerImproving the efficiency of adversarial robustness defenses
Technical noteFive ways IBM is using synthetic data to improve AI models
ResearchA new way to generate synthetic data for pretraining computer vision models
NewsSecuring AI systems with adversarial robustness
Deep Dive- See more of our work on Data and AI Security
Projects
Federated systems
- Data and AI Security
- Adversarial Robustness and Privacy
- Foundation Models
Testing for AI
- Data and AI Security
Data quality in AI
- Data and AI Security
Metadata management
- Data and AI Security
Privacy enhancing technologies for regulatory compliance
- Data and AI Security
Publications
- 2023
- NDSS 2023
- 2023
- NDSS 2023
- 2022
- Big Data 2022
- 2022
- ACM CCS 2022
- 2022
- AMIA Annual Symposium 2022
- 2022
- MICRO 2022
IBM Solution: IBM Cloud Pak for Data
Our research is regularly incorporated into new security features for IBM Cloud Pak for Data.
Tools + code
ART: Adversarial Robustness Toolbox
A Python library for machine learning security that enables developers and researchers to defend and evaluate machine learning models and applications against the adversarial threats of evasion, poisoning, extraction, and inference.
View project →AI Privacy 360
Tools to support the assessment of privacy risks of AI-based solutions, and to help them adhere to any relevant privacy requirements. Tradeoffs between privacy, accuracy, and performance can be explored at different stages in the machine learning lifecycle.
View project →Diffprivlib: The IBM Differential Privacy Library
A general-purpose library for experimenting with, investigating, and developing applications in differential privacy.
View project →IBM Federated Learning - Community Edition
A Python framework for federated learning in an enterprise environment.
View project →HELayers – Community Edition
SDKs for computing on encrypted data without decrypting it, provided via Docker container. Equipped with C++ and Python API’s and includes Jupyter Notebooks and VS Code IDEs with demonstrations, tutorials and documentation for AI/ML and encrypted search applications. Support for Linux, Intel, MacOS and s390x platforms.
View project →
