Publications

OverThink: Slowdown Attacks on Reasoning LLMs (CODE)

Abhinav Kumar, Jaechul Roh, Ali Naseh, Marzena Karpiska, Mohit Iyyer, Amir Houmansadr, Eugene Bagdasarian

LATTEO: A Framework to Support Learning Asynchronously Tempered with Trusted Execution and Obfuscation

Abhinav Kumar, George Torres, Noah Guzinski, Gaurav Panwar, Reza Tourani, Satyajayant Misra, Marcin Spoczynski, Mona Vij, Nageen Himayat

Privacy Analysis of Oblivious DNS over HTTPS: a Website Fingerprinting Study (IEEE DSN 2025)

Mohammad Salari, Abhinav Kumar, Federico Rinaudi, Reza Tourani, Alessio Sacco, Flavio Esposito

Persistent Backdoor Attacks in Continual Learning (USENIX Security 2025) (CODE)

Zhen Guo, Abhinav Kumar, Reza Tourani

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability

Chenxi Li, Abhinav Kumar, Zhen Guo, Jie Hou, Reza Tourani

Silver Linings in the Shadows: Harnessing Membership Inference for Machine Unlearning

Nexhi Sula, Abhinav Kumar, Jie Hou, Han Wang, Reza Tourani

A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference (ACM ASIACCS 2024) (CODE)

Abhinav Kumar, Miguel A. Guirao Aguilera, Reza Tourani, Satyajayant Misra

A Stealthy Inference Attack on Split Learning with a Split-Fuse Defensive Measure (IEEE CNS 2023)

Sean Dougherty,  Abhinav Kumar,  Jie Hou , Reza Tourani ,  Atena M. Tabakhi

IoT Sentinel: Correlation-based Attack Detection, Localization, and Authentication in IoT Networks (IEEE ICCCN 2023)

Dianshi Yang, Abhinav Kumar, Stuart Ray, Wei Wang, Reza Tourani