Tag Archives: ML

A Method to Facilitate Membership Inference Attacks in Deep Learning Models

Zitao Chen and Karthik Pattabiraman, To appear in the Network and Distributed Systems Security Symposium (NDSS), 2025. (Acceptance Rate: TBD) [ PDF | Talk ] (Code) (arXIV version). Artifacts Available, Functional and Results Reproduced.
Continue reading

Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models

Qutub Syed, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn1, Fabian Oboril, Cornelius Buerkle, Kay-Ulrich Scholl, Gereon Hinz and Alois Knoll, Proceedings of the IJCAI-AISafety Workshop, 2024. [ PDF | Talk ]
Continue reading

Harnessing Explainability to Improve ML Ensemble Resilience

Abraham Chan, Arpan Gujarati, Karthik Pattabiraman and Sathish Gopalakrishnan, Supplementary proceedings of the IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2024. Disrupt Track. (Acceptance Rate: TBD) [ PDF | Talk ]
Continue reading

Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

Zitao Chen and Karthik Pattabiraman, Proceedings of the Network and Distributed Systems Security Conference (NDSS), 2024. (Acceptance Rate: 15%). [ PDF | Talk ] (ArXIV, Code). Artifacts Available, Functional and Reproduced
Continue reading

Evaluating the Effect of Common Annotation Faults on Object Detection Techniques

Abraham Chan, Arpan Gujarati, Karthik Pattabiraman and Sathish Gopalakrishnan, Proceedings of the IEEE International Symposium on Software Reliability Engineering (ISSRE), 2023. (Acceptance Rate: 28.5%) [ PDF | Talk ] (Code). Artifacts Available and Reviewed.

Continue reading

Resilience Assessment of Large Language Models under Transient Hardware Faults

Udit Agarwal, Abraham Chan, and Karthik Pattabiraman, Proceedings of the IEEE International Symposium on Software Reliability Engineering (ISSRE), 2023. (Acceptance Rate: 28.5%) [ PDF | Talk ] (Code). Artifacts Available and Reviewed.
Continue reading

Towards Reliability Assessment of Systolic Arrays against Stuck-at Faults

Udit Kumar Agarwal, Abraham Chan, Ali Asgari, and Karthik Pattabiraman. 19th IEEE Workshop on Silicon Errors in Logic – System Effects (SELSE), 2023. Received Best-of-SELSE award (one of three papers). Invited for presentation at DSN’23. [ PDF  | Presentation ] (Code)
Continue reading

Structural Coding: A Low-Cost Scheme to Protect CNNs from Large-Granularity Memory Faults

Ali Asgari, Florian Geissler, Syed Qutub, Michael Paulitsch, Prashant Nair, and Karthik Pattabiraman, Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2023. (Acceptance Rate: 23.9%) [ PDF | Talk ] (code). Artifacts Available and Functional
Continue reading

A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks

Florian Geissler, Syed Qutub, Michael Paulitsch and Karthik Pattabiraman, Proceedings of the International Conference on Computer Safety, Reliability and Security (SafeComp), 2023. (Acceptance Rate: 20%) [PDF | Talk]
Continue reading

Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

Zitao Chen, Pritam Dash, and Karthik Pattabiraman. Proceedings of the 18th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS), 2023. (Acceptance Rate: 16%) [ PDF | Talk ] (code)
Continue reading