The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

The majority of machine learning methodologies operate with the assumption that their
environment is benign. However, this assumption does not always hold, as it is often …

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep
neural networks in which participants' data remains on their own devices with only model …

Deep neural networks and machine-learning algorithms are pervasively used in several
applications, ranging from computer vision to computer security. In most of these …

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training
datasets. This is cheaper than labeling datasets manually, and even improves out-of …

With the widespread use of deep learning system in many applications, the adversary has
strong incentive to explore vulnerabilities of deep neural networks and manipulate them …

Abstract Machine learning systems trained on user-provided data are susceptible to data
poisoning attacks, whereby malicious users inject false training data with the aim of …

A number of online services nowadays rely upon machine learning to extract valuable
information from data collected in the wild. This exposes learning algorithms to the threat of …

Currently, Machine Learning (ML) is becoming ubiquitous in everyday life. Deep Learning
(DL) is already present in many applications ranging from computer vision for medicine to …

Machine learning is one of the most prevailing techniques in computer science, and it has
been widely applied in image processing, natural language processing, pattern recognition …