Siddharth Garg

SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

2017 · arXiv (Cornell University)

Inference using deep neural networks is often outsourced to the cloud since it is a computationally demanding task. However, this raises a fundamental issue of trust. How can a client be sure that the cloud …

Optimal Active Social Network De-anonymization Using Information Thresholds

2018 · arXiv (Cornell University)

In this paper, de-anonymizing internet users by actively querying their group memberships in social networks is considered. In this problem, an anonymous victim visits the attacker's website, and the attacker uses the victim's browser history …

Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection

2023 · arXiv (Cornell University)

This paper proposes a data-efficient detection method for deep neural networks against backdoor attacks under a black-box scenario. The proposed approach is motivated by the intuition that features corresponding to triggers have a higher influence …