Author Archives: karthikp

A Method to Facilitate Membership Inference Attacks in Deep Learning Models

Posted on June 22, 2024 | Comments Off on 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 (Coming soon) | Talk ] (Code)
Continue reading →

Comments Off on A Method to Facilitate Membership Inference Attacks in Deep Learning Models

Posted in papers

Tagged , , , ,

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

Posted on June 6, 2024 | Comments Off on 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, To appear in the Proceedings of the IJCAI-AISafety Workshop, 2024. [ PDF (coming soon) | Talk ]
Continue reading →

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

Posted in papers

Tagged , , , ,

Co-Approximator: Enabling Performance Prediction in Colocated Applications

Posted on May 18, 2024 | Comments Off on Co-Approximator: Enabling Performance Prediction in Colocated Applications

Mohammad Rafiuzzaman, Sathish Gopalakrishnan and Karthik Pattabiraman, To appear in the ACM Transactions on Embedded Computing Systems (TECS). Acceptance Date: May 2024. [ PDF ]
Continue reading →

Comments Off on Co-Approximator: Enabling Performance Prediction in Colocated Applications

Posted in papers

Tagged , , , ,

Harnessing Explainability to Improve ML Ensemble Resilience

Posted on April 29, 2024 | Comments Off on 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 →

Comments Off on Harnessing Explainability to Improve ML Ensemble Resilience

Posted in papers

Tagged , , , ,

POMABuster: Detecting Price Oracle Manipulation Attacks in Decentralized Finance

Posted on March 9, 2024 | Comments Off on POMABuster: Detecting Price Oracle Manipulation Attacks in Decentralized Finance

Rui Xi, Zehua Wang, and Karthik Pattabiraman, Proceedings of the IEEE Symposium on Security and Privacy (S&P), 2024. (Acceptance Rate: 17.8%) [ PDF | Talk] (Code)
Continue reading →

Comments Off on POMABuster: Detecting Price Oracle Manipulation Attacks in Decentralized Finance

Posted in papers

Tagged , , , ,

Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems

Posted on February 16, 2024 | Comments Off on Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems

Mohammad ElNawawy, Mohammadreza Hallajiyan, Gargi Mitra, Shahrear Iqbal, and Karthik Pattabiraman, Proceedings of the IEEE/ACM international conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) (CHASE 2024). (Acceptance Rate: 28.4%) [ PDF | Talk ] (arXIV version, Code&data)
Continue reading →

Comments Off on Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems

Posted in papers

Tagged , , , , , , ,

ImmunoPlane: Middleware for Providing Adaptivity to Distributed Internet-of-Things Applications

Posted on January 19, 2024 | Comments Off on ImmunoPlane: Middleware for Providing Adaptivity to Distributed Internet-of-Things Applications

Kumseok Jung, Gargi Mitra, Sathish Gopalakrishnan and Karthik Pattabiraman, Proceedings of the ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI), 2024. (Acceptance Rate: TBD) [ PDF | Talk] (code)
Continue reading →

Comments Off on ImmunoPlane: Middleware for Providing Adaptivity to Distributed Internet-of-Things Applications

Posted in papers

Tagged , , , , , ,

Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks

Posted on December 19, 2023 | Comments Off on Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks

Pritam Dash, Guanpeng Li, Mehdi Karimibiuki, and Karthik Pattabiraman, To appear in the ACM Asia Conference on Computer and Communications Security (AsiaCCS), 2024. (Acceptance Rate: TBD) [PDF | Talk] (Code) (arXIV version)
Continue reading →

Comments Off on Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks

Posted in papers

Tagged , , , , , ,

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

Posted on December 2, 2023 | Comments Off on 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 →

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

Posted in papers

Tagged , , , ,

Characterizing and Improving Resilience of Accelerators to Memory Errors in Autonomous Robots

Posted on September 24, 2023 | Comments Off on Characterizing and Improving Resilience of Accelerators to Memory Errors in Autonomous Robots

Deval Shah, Zi Yu Xue, Karthik Pattabiraman and Tor Aamodt, To appear in the ACM Transactions on Cyber-Physical Systems (TCPS). (Acceptance date: Sep 2023). [PDF] (arXIV)
Continue reading →

Comments Off on Characterizing and Improving Resilience of Accelerators to Memory Errors in Autonomous Robots

Posted in papers

Tagged , , ,