Related papers: AdaPI: Facilitating DNN Model Adaptivity for Effic…

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire of a skewed distribution of data labels across participants…

With the rapid advancement of large models and mobile edge computing, transfer learning, particularly through fine-tuning, has become crucial for adapting models to downstream tasks. Traditionally, this requires users to share their data…

The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allow parties to perform inference without revealing their…

Differential Privacy (DP) is the leading approach to privacy preserving deep learning. As such, there are multiple efforts to provide drop-in integration of DP into popular frameworks. These efforts, which add noise to each gradient…

As Deep Neural Network (DNN) inference becomes increasingly prevalent on edge and mobile platforms, critical challenges emerge in privacy protection, resource constraints, and dynamic model deployment. This paper proposes a privacy-aware…

Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predominantly on fixed gradient clipping thresholds. Such static clipping neglects significant…

The ability to perform computation on devices, such as smartphones, cars, or other nodes present at the Internet of Things leads to constraints regarding bandwidth, storage, and energy, as most of these devices are mobile and operate on…

With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This…

Despite the recent progress of network pruning, directly applying it to the Internet of Things (IoT) applications still faces two challenges, i.e. the distribution divergence between end and cloud data and the missing of data label on end…

Hyperparameter optimization is a ubiquitous challenge in machine learning, and the performance of a trained model depends crucially upon their effective selection. While a rich set of tools exist for this purpose, there are currently no…

The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural…

Existing approaches for training neural networks with user-level differential privacy (e.g., DP Federated Averaging) in federated learning (FL) settings involve bounding the contribution of each user's model update by clipping it to some…

Collaborative deep learning inference between low-resource endpoint devices and edge servers has received significant research interest in the last few years. Such computation partitioning can help reducing endpoint device energy…

The proliferation of the Internet of Things (IoT) and its cutting-edge AI-enabled applications (e.g., autonomous vehicles and smart industries) combine two paradigms: data-driven systems and their deployment on the edge. Usually, edge…

Humans have the ability to adapt the type of information they use, the procedure they employ, and the amount of time they spend when solving problems. However, most standard neural networks have a fixed function type and computation budget…

We present two efficient numerical methods for susceptibility artifact correction applicable in Echo Planar Imaging (EPI), an ultra fast Magnetic Resonance Imaging (MRI) technique widely used in clinical applications. Both methods address a…

In many science and engineering settings, system dynamics are characterized by governing PDEs, and a major challenge is to solve inverse problems (IPs) where unknown PDE parameters are inferred based on observational data gathered under…

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…

Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently,…

Wi-Fi/RF-based human sensing has achieved remarkable progress with deep learning, yet practical deployments increasingly require feature sharing for cloud analytics, collaborative training, or benchmark evaluation. Releasing intermediate…