vimokumar / stride-ai

STRIDE-AI

STRIDE-AI is an ML-specific, asset-centered methodology for identifying threats to AI-based systems.

Below are the reference papers:

L. Mauri and E. Damiani, "STRIDE-AI: An Approach to Identifying Vulnerabilities of Machine Learning Assets," 2021 IEEE International Conference on Cyber Security and Resilience (CSR), 2021, pp. 147-154, doi: 10.1109/CSR51186.2021.9527917.

L. Mauri and E. Damiani, "Modeling Threats to AI-ML Systems Using STRIDE," Sensors. 2022; 22(17):6662. doi: 10.3390/s22176662.

---

Additional material:

1. Failure Mode and Effects Analysis of AI-ML Systems
   
2. ML Assets and their Failure Modes
3. Mapping ML Assets' Failure Modes to CIA³-R Hexagon
4. Case Study: LIGHT-TOREADOR Platforms

--> Further material will be added shortly!

---

Contributors

Lara Mauri¹ and Ernesto Damiani^1,2

¹ Computer Science Department, Università degli Studi di Milano, Milan, Italy
² Center for Cyber Physical Systems (C2PS), Khalifa University, Abu Dhabi, UAE