Thinking Inside the Box: Injecting Realistic Radiation Faults in ML Accelerators
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This repository contains both the code and data artifacts for the DSN 2026 paper "Thinking Inside the Box: Injecting Realistic Radiation Faults in ML Accelerators". The code artifact is in the folder "TPU-FI_DSN26_AE" while the data artifact is in the folder "Data_DSN26_AE". This repository contains 2 versions of the artifact. The version2 has additional instructions for generating plots and comparing results with those in the paper.
Fields of Study & Subjects
Radiation Effects in Electronics
Software Testing and Debugging Techniques
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 24 March 2026
- Language
- EN