Publications

Investigating The Impact of Transient Hardware Faults on Deep Learning Neural Network Inference
Md Hasanur Rahman, Sabuj Laskar, Guanpeng Li
[STVR’24][Fault Tolerance]: Software Testing, Verification and Reliability, 2024
[Paper] [Slides] [Code] [Cite]

DRUTO: Upper-Bounding Silent Data Corruption Vulnerability in GPU Applications
Md Hasanur Rahman, Sheng Di, Shengjian Guo, Xiaoyi Lu, Guanpeng Li, and Franck Cappello
[IPDPS’24][Fault Tolerance]: The 38th IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2024
[Paper] [Slides] [Code] [Cite]

A Feature-Driven Fixed-Ratio Lossy Compression Framework for Real-World Scientific Datasets
Md Hasanur Rahman, Sheng Di, Kai Zhao, Robert Underwood, Guanpeng Li, and Franck Cappello
[ICDE’23][Lossy Compression]: The 39th IEEE International Conference on Data Engineering, 2023 (Acceptance rate: 19.1% past years)
[Paper] [Slides] [Code] [Cite]

Characterizing Deep Learning Neural Network Failures between Algorithmic Inaccuracy and Transient Hardware Faults
Sabuj Laskar, Md Hasanur Rahman, Bohan Zhang, and Guanpeng Li
[PRDC’22][Fault Tolerance]: The 27th IEEE Pacific Rim International Symposium on Dependable Computing, 2022
[Paper] [Slides] [Code] [Cite]

TensorFI+: A Scalable Fault Injection Framework for Modern Deep Learning Neural Networks
Sabuj Laskar, Md Hasanur Rahman, and Guanpeng Li
[ISSRE-W’22][Fault Tolerance]: Workshop on Resiliency, Security, Defenses, and Attacks (RSDA) at IEEE International Symposium on Software Reliability Engineering, 2022
[Paper] [Slides] [Code] [Cite]

PEPPA-X: finding program test inputs to bound silent data corruption vulnerability in HPC applications
Md Hasanur Rahman, Aabid Shamji, Shengjian Guo, and Guanpeng Li
[SC’21][Fault Tolerance]: International Conference for High Performance Computing, Networking, Storage and Analysis, 2021 (Acceptance rate: 23.6%)
[Paper] [Slides] [Code] [Cite]
Received all three artifacts badges