Tag Archives: Resilient

LLTFI: Framework Agnostic Fault Injection for Machine Learning Applications

Udit Agarwal, Abraham Chan, and Karthik Pattabiraman, IEEE International Symposium on Software Reliability Engineering (ISSRE), 2022. (Acceptance Rate: 29%) [ PDF | Talk (video) ] (Code)
Continue reading

Fault Injection for TensorFlow Applications

Niranjhana Narayanan, Zitao Chen, Bo Fang, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, IEEE Transactions on Dependable and Secure Computing (TDSC). Acceptance Date: May 2022. [ PDF ] (code1, code2)
Continue reading

The Fault in Our Data Stars: Studying Mitigation Techniques against Faulty Training Data in ML Applications

Abraham Chan, Arpan Gujarati, Karthik Pattabiraman, and Sathish Gopalakrishnan. IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2022. (Acceptance rate: 18.7%) [ PDF | Talk ] (Code)
Continue reading

Understanding the Resilience of Neural Network Ensembles against Faulty Training Data

Abraham Chan, Niranjhana Narayananan, Arpan Gujarati, Karthik Pattabiraman, and Sathish Gopalakrishnan, IEEE International Symposium on Quality, Reliability and Security (QRS), 2021. Full paper (Acceptance Rate: 25.1%) [ PDF | Talk | Video ] Best Paper Award (1 of 3)

Continue reading

Towards a safety case for hardware-fault tolerance in convolutional neural networks using activation range supervision

Florian Geissler, Syed Qutub, Sayanta Roychowdhury, Ali Asgari, Yang Peng, Akash Dhamasia, Ralf Graefe, Karthik Pattabiraman and Michael Paulitsch, AI Safety Workshop 2021, Best Paper Award Nominee (1 of 4) [ PDF | Talk ] (arXIV)
Continue reading

A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction

Zitao Chen, Guanpeng Li, and Karthik Pattabiraman, IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2021. (Acceptance Rate: 16.5%). [ PDF | Talk , Video] (arXIV, code) Best Paper Award Runner up (1 of 2 among nearly 300 submissions). Incorporated into Intel’s OpenVino2 Framework (More details, Documentation).
Continue reading

An Empirical Study of the Impact of Single and Multiple Bit-Flip Errors in Programs

Behrooz Sangchoolie, Karthik Pattabiraman and Johan Karlsson, To appear in the IEEE Transactions on Dependable and Secure Computing (TDSC). [ PDF ]
Continue reading

New Wine in an Old Bottle: N-Version Programming for Machine Learning Components

Arpan Gujarati, Sathish Gopalakrishnan, and Karthik Pattabiraman, IEEE International Workshop on Software Certification (WoSoCER), 2020. Held in conjunction with the IEEE International Symposium on Software Reliability Engineering (ISSRE), 2020. [PDF][Talk]
Continue reading

How Far Have We Come in Detecting Anomalies in Distributed Systems? An Empirical Study with a Statement-level Fault Injection Method

Yong Yang, Yifan Yu, Karthik Pattabiraman, Long Wang, Ying Li, IEEE International Symposium on Software Reliability Engineering (ISSRE), 2020. (Acceptance Rate: 26%). [ PDF | Talk ] (Code)
Continue reading

TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Zitao Chen, Niranjhana Narayanan, Bo Fang, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, IEEE International Symposium on Software Reliability Engineering (ISSRE), 2020. (Acceptance Rate: 26%) [ PDF | Talk ] (Code)
Continue reading