The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

In recent years, machine learning has transitioned from a field of academic research interest
to a field capable of solving real-world business problems. However, the deployment of …

Deep learning models are often trained on distributed, webscale datasets crawled from the
internet. In this paper, we introduce two new dataset poisoning attacks that intentionally …

Federated learning (FL) is a new breed of Artificial Intelligence (AI) that builds upon
decentralized data and training that brings learning to the edge or directly on-device. FL is a …

While recent works have indicated that federated learning (FL) may be vulnerable to
poisoning attacks by compromised clients, their real impact on production FL systems is not …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

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 …

Lithium-ion batteries are ubiquitous in applications ranging from portable electronics to
electric vehicles. Irrespective of the application, reliable real-time estimation of battery state …

Federated learning (FL) enables many data owners (eg, mobile devices) to train a joint ML
model (eg, a next-word prediction classifier) without the need of sharing their private training …

Deep machine unlearning is the problem of'removing'from a trained neural network a subset
of its training set. This problem is very timely and has many applications, including the key …