Measuring Linkability of Protected Biometric Templates Using Maximal Leakage

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probab ...

The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private observation ...

A robust capacitive multisensory readout system is presented in this article. The system consists of a few thousand lossy capacitive-based sensors that can be modeled as a parallel connection of sensor capacitor and undesirable leakage resistance. The real ...

This paper presents a numerical study assessing the seismic performance of steel moment-resisting frames (SMRFs) designed with ductile exposed column-base plate (ECBP) connections employing yielding anchor rods. For their potential use as weak bases, the p ...

Existing works for depth estimation and image deblurring in the presence of depth-dependent blur work with the assumption of a multi-layered scene wherein each layer is modeled in the form of a fronto-parallel plane. In this work, we attempt to relax these ...

Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression wit ...

Loop closure detection helps simultaneous localization and mapping systems reduce map and state uncertainty via recognizing previously visited places along the path of a mobile robot. However, visual loop closure detection is susceptible to scenes with dyn ...

The Matching Augmentation Problem (MAP) has recently received significant attention as an important step towards better approximation algorithms for finding cheap 2-edge connected subgraphs. This has culminated in a 5/3-approximation algorithm. However, th ...

III-N light-emitting-diodes (LEDs) are subject of intense investigations, thanks to their high efficiency and great reliability. The quality of the semiconductor material has a significant impact on the electro-optical performance of LEDs: for this reason, ...

Offshore wind farm modelling has been an area of rapidly increasing interest over the last two decades, with numerous analytical as well as computational-based approaches developed, in an attempt to produce designs that improve wind farm efficiency in powe ...

Although encryption hides the content of communications from third parties, metadata, i.e., the information attached to the content (such as the size or timing of communication) can be a rich source of details and context. In this dissertation, we demonstr ...

Background. Latencies of motor evoked potentials (MEPs) can provide insights into the motor neuronal pathways activated by transcranial magnetic stimulation. Notwithstanding its clinical relevance, accurate, unbiased methods to automatize latency detection ...

Determining the relationship between the cause of damage and the subsequent structural behavior of infrastructure systems requires an accurate characterization of the propagation of cracks, which represents the evolution of the damage state. When no inform ...

This study investigates the use of a low cost microphone combined with state-of-the-art machine learning (ML) algorithms as online process monitoring to differentiate various materials and process regimes of Laser-Powder Bed Fusion (LPBF). Three processing ...

This paper explores the use of sliding friction dampers (SFDs) as dissipative floor connectors to mitigate higher mode effects and earthquake-induced absolute acceleration demands on steel concentrically braced frame (CBF) buildings. The dampers connect ea ...

We demonstrate a hybrid photonic integrated laser with intrinsic linewidth of 40 Hz, while offering megahertz actuation bandwidth with the tuning range larger than 1 GHz, attained by a DFB laser self-injection locking to a high-Q Si3N4 microresonator with ...

This paper proposes a novel technique for the design of miniaturized Ka-band filters based on locally resonant metamaterials (LRMs), which are fabricated monolithically using lost wax casting. We implement ultra-small metamaterial filters by exploiting a n ...

Internet-of-Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency chall ...

The RESTRICTED ASSIGNMENT problem is a prominent special case of SCHEDULING ON UNRELATED PARALLEL MACHINES. For the strongest known linear programming relaxation, the configuration LP, we improve the nonconstructive bound on its integrality gap from 1.9412 ...

Measuring Linkability of Protected Biometric Templates Using Maximal Leakage

Chat with Graph Search

Global Group Fairness in Federated Learning via Function Tracking

Discovering Influencers in Opinion Formation Over Social Graphs

Robust Analog Multisensory Array System for Lossy Capacitive Sensors Over Long Distances

Probabilistic seismic performance assessment of steel moment-resisting frames considering exposed column-base plate connections with ductile anchor rods

Multi-planar geometry and latent image recovery from a single motion-blurred image

Non-Structured DNN Weight Pruning--Is It Beneficial in Any Platform?

PlaceNet: A multi-scale semantic-aware model for visual loop closure detection

A Simple LP-Based Approximation Algorithm for the Matching Augmentation Problem

Defects in III-N LEDs: experimental identification and impact on electro-optical characteristics

Offshore wind farm wake modelling using deep feed forward neural networks for active yaw control and layout optimisation

Protecting privacy through metadata analysis

Greenberg's Force Prediction for Vertical-Axis Wind Turbine Blades

An automatized method to determine latencies of motor-evoked potentials under physiological and pathophysiological conditions

Determining crack kinematics from imaged crack patterns

Differentiation of materials and laser powder bed fusion processing regimes from airborne acoustic emission combined with machine learning

Seismic design and performance of steel concentrically braced frame buildings with dissipative floor connectors

Low-noise, Frequency-agile, Hybrid Integrated Laser for LiDAR

Ultra-Compact Ka-band Metamaterial Waveguide Filters, Fabricated by Lost-Wax Casting

A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics

A Quasi-Polynomial Approximation For The Restricted Assignment Problem