Defending Against Free-Riders Attacks in Distributed Generative Adversarial Networks

Generative Adversarial Networks (GANs) are increasingly adopted by the industry to synthesize realistic images using competing generator and discriminator neural networks. Due to data not being centrally available, Multi-Discriminator (MD)-GANs training frameworks employ multiple discriminators that have direct access to the real data....

Fabricated Flips: Poisoning Federated Learning without Data

Attacks on Federated Learning (FL) can severely reduce the quality of the generated models and limit the usefulness of this emerging learning paradigm that enables on-premise decentralized learning. However, existing untargeted attacks are not practical for many scenarios as they assume that i) the attacker knows every update of benign...

GDTS: GAN-Based Distributed Tabular Synthesizer

Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. While learning image GANs on Federated Learning (FL) and Multi-Discriminator (MD) systems has just been demonstrated, it is unknown if tabular GANs can be learned...

FCT-GAN: Enhancing Global Correlation of Table Synthesis via Fourier Transform

An alternative method for sharing knowledge while complying with strict data access regulations, such as the European General Data Protection Regulation (GDPR), is the emergence of synthetic tabular data. Mainstream table synthesizers utilize methodologies derived from Generative Adversarial Networks (GAN). Although several state-of-the-art ...

DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints

Backdoor attack is a type of serious security threat to deep learning models. An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output incorrect prediction if the input is stamped...

WEDAR: Webcam-based Attention Analysis via Attention Regulator Behavior Recognition with a Novel E-reading Dataset

Human attention is critical yet challenging cognitive process to measure due to its diverse definitions and non-standardized evaluation. In this work, we focus on the attention self-regulation of learners, which commonly occurs as an effort to regain focus, contrary to attention loss. We focus on easy-to-observe behavioral signs in the real...

Permutation-Invariant Tabular Data Synthesis

Tabular data synthesis is an emerging approach to circumvent strict regulations on data privacy while discovering knowledge through big data. Although state-of-the-art AI-based tabular data synthesizers, e.g., table-GAN, CTGAN, TVAE, and CTAB-GAN, are effective at generating synthetic tabular data, their training is sensitive to column...

A 2m-Range 711uW Body Channel Communication Transceiver Featuring Dynamically-Sampling Bias-Free Interface Front End

Body Channel Communication (BCC) offers a low-loss signal transmission medium for ultra-low-power wearable devices on human body [1]. However, the effective communication range on human body is limited to less than 1m in the state-of-the-art BCC transceivers [2], where the signal loss at the interface of body surface and BCC receiver remains to...

Federated Learning for Tabular Data: Exploring Potential Risk to Privacy

Federated Learning (FL) has emerged as a potentially powerful privacy-preserving machine learning method-ology, since it avoids exchanging data between participants, but instead exchanges model parameters. FL has traditionally been applied to image, voice and similar data, but recently it has started to draw attention from domains including...

Developing AI into explanatory supporting models: An explanation-visualized deep learning prototype

Using Artificial Intelligence (AI) and machine learning technologies to automatically mine latent patterns from educational data holds great potential to inform teaching and learning practices. However, the current AI technology mostly works as "black box"-only the inputs and the corresponding outputs are available, which largely impedes...

An Exploratory Analysis on Users' Contributions in Federated Learning

Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition. Its core principle is to learn from large amount of users data while preserving data privacy by design as collaborative users only need to share the machine learning models...

Progress in multiscale computational electromagnetics in time domain

Many system-level electromagnetic design problems are multiscale and very challenging to solve. They remain a significant barrier to system design optimization for a foreseeable future. Such multiscale problems often contain three electrical scales, i.e., the fine scale (geometrical feature size much smaller than a wavelength), the coarse scale ...