Tag Archives: ML

Understanding the Resilience of Neural Network Ensembles against Faulty Training Data

Posted on October 22, 2021 by | Comments Off on 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 →

Comments Off on Understanding the Resilience of Neural Network Ensembles against Faulty Training Data

Posted in papers

Tagged , , , , , , , ,

(WiP) LLTFI: Low-Level Tensor Fault Injector

Posted on August 31, 2021 by | Comments Off on (WiP) LLTFI: Low-Level Tensor Fault Injector

Abraham Chan, Udit Agarwal, and Karthik Pattabiraman. IEEE International Workshop on Software Certification (WoSoCER’21), co-held with the IEEE International Symposium on Software Reliability Engineering (ISSRE), 2021. [ PDF | Talk ] (Code)
Continue reading →

Comments Off on (WiP) LLTFI: Low-Level Tensor Fault Injector

Posted in papers

Tagged , , , , ,

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

Posted on August 21, 2021 by | Comments Off on 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 →

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

Posted in papers

Tagged , , , , ,

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

Posted on March 10, 2021 by | Comments Off on 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 →

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

Posted in papers

Tagged , , , , , , , ,

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

Posted on September 1, 2020 by | Comments Off on 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 →

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

Posted in papers

Tagged , , , , ,

TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Posted on August 14, 2020 by | Comments Off on 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 →

Comments Off on TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Posted in papers

Tagged , , , , , , , ,

BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Posted on June 16, 2019 by | Comments Off on BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Zitao Chen, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2019. (Acceptance Rate: 21%) [ PDF | Talk ] ( Code Finalist for the SC reproducibility challenge (one of 3 papers))
Continue reading →

Comments Off on BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Posted in papers

Tagged , , , , , ,

Understanding Error Propagation in Deep-Learning Neural Networks (DNN) Accelerators and Applications

Posted on June 15, 2017 by | Comments Off on Understanding Error Propagation in Deep-Learning Neural Networks (DNN) Accelerators and Applications

Guanpeng Li, Siva Hari, Michael Sullivan, Timothy Tsai, Karthik Pattabiraman, Joel Emer, Stephen Keckler, International Conference for High-Performance Computing, Networking, Storage and Analysis (SC), 2017. (Acceptance Rate: 19%) [PDF | Talk] (Injector code)
Chosen for IEEE Top Picks in Test and Reliability (TPTR), 2023.
Continue reading →

Comments Off on Understanding Error Propagation in Deep-Learning Neural Networks (DNN) Accelerators and Applications

Posted in papers

Tagged , , , , , ,