We investigate a new method for injecting backdoors into machine learning models, based
on compromising the loss-value computation in the model-training code. We use it to …

Deep learning models have consistently outperformed traditional machine learning models
in various classification tasks, including image classification. As such, they have become …

Machine learning (ML) has made tremendous progress during the past decade and is being
adopted in various critical real-world applications. However, recent research has shown that …

Deep learning models have consistently outperformed traditional machine learning models
in various classification tasks, including image classification. As such, they have become …

Lack of transparency in deep neural networks (DNNs) make them susceptible to backdoor
attacks, where hidden associations or triggers override normal classification to produce …

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs).
While existing defense methods have demonstrated promising results on detecting or …

When machine learning training is outsourced to third parties, $ backdoor $$ attacks $
become practical as the third party who trains the model may act maliciously to inject hidden …

Recent work proposed the concept of backdoor attacks on deep neural networks (DNNs),
where misclassification rules are hidden inside normal models, only to be triggered by very …

With the prevalent use of Deep Neural Networks (DNNs) in many applications, security of
these networks is of importance. Pre-trained DNNs may contain backdoors that are injected …

Deep learning models are vulnerable to various adversarial manipulations of their training
data, parameters, and input sample. In particular, an adversary can modify the training data …