Artificial Intelligence (AI) relies heavily on deep learning-a technology that is becoming
increasingly popular in real-life applications of AI, even in the safety-critical and high-risk …

Backdoor inversion, the process of finding a backdoor trigger inserted into a machine
learning model, has become the pillar of many backdoor detection and defense methods …

In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when
presented with clean samples versus poisoned samples. Our analysis shows significant …

Deep Neural Networks (DNNs) are ubiquitous and span a variety of applications ranging
from image classification to real-time object detection. As DNN models become more …

The extensive applications of deep neural network (DNN) and its increasingly complicated
architecture and supply chain make the risk of backdoor attacks more realistic than ever. In …

Collecting training data from untrusted sources exposes machine learning services to
poisoning adversaries, who maliciously manipulate training data to degrade the model …

Deep learning, as an important branch of machine learning, has been widely applied in
computer vision, natural language processing, speech recognition, and more. However …

In recent years, more researchers pay their attention to the security of artificial intelligence.
The backdoor attack is one of the threats and has a powerful, stealthy attack ability. There …

Learning utility, or reward, models from pairwise comparisons is a fundamental component
in a number of application domains. These approaches inherently entail collecting …

This work proposes a definition and examines the problem of undetectably engraving
special input/output information into a Neural Network (NN). Investigation of this problem is …