Most existing methods to detect backdoored machine learning (ML) models ...
In this paper, we present a simple yet surprisingly effective technique ...
With extensive studies on backdoor attack and detection, still fundament...
As an emerging technique for confidential computing, trusted execution
e...
Trusted execution environments (TEE) such as Intel's Software Guard Exte...
A trusted execution environment (TEE) such as Intel Software Guard Exten...
The number of linear regions is one of the distinct properties of the ne...
Domain Adaptation (DA) targets at adapting a model trained over the
well...
A security threat to deep neural networks (DNN) is backdoor contaminatio...
It has been a long standing problem to securely outsource computation ta...
Membership Inference Attack (MIA) determines the presence of a record in...
We propose smooth q-gram, the first variant of q-gram that captures
q-gr...