collaborators

6 papers

cs.CR2025

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs

Zhen Guo, Shanghao Shi, Shamim Yazdani +2

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their compl…

cs.LG2025

Persistent Backdoor Attacks in Continual Learning

Zhen Guo, Abhinav Kumar, Reza Tourani

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially…

cs.CR2025

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

Abhinav Kumar, George Torres, Noah Guzinski +6

The privacy vulnerabilities of the federated learning (FL) paradigm, primarily caused by gradient leakage, have prompted the development of various defensive measures. Nonetheless,…

cs.LG2024

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

Nexhi Sula, Abhinav Kumar, Jie Hou +2

With the continued advancement and widespread adoption of machine learning (ML) models across various domains, ensuring user privacy and data security has become a paramount concer…

cs.LG2024

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

Chenxi Li, Abhinav Kumar, Zhen Guo +2

The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inf…

cs.CR2024

A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference

Abhinav Kumar, Miguel A. Guirao Aguilera, Reza Tourani +1

The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privac…