Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Correlational Power Analysis: Efficient CNN Architectures

Description

This lecture covers the methodology for efficient CNN architectures in profiling attacks, focusing on correlational power analysis, feature selection, and recommendations for designing CNNs. It also discusses results from a DPA contest and references related work.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructor

Serge Vaudenay

Serge Vaudenay entered at the Ecole Normale Supérieure in 1989 with a major in mathematics. He earned his agrégation (secondary teaching degree) in mathematics in 1992, then a PhD in Computer Science at the University of Paris 7 - Denis Diderot in 1995. He subsequently became a senior research fellow at the CNRS, prior to being granted his habilitation à diriger des recherches (a postdoctoral degree authorizing the recipient to supervise doctoral students). In 1999, he was appointed as a Professor at the EPFL, where he created the Security and Cryptography Laboratory.

Official source

Related concepts (32)

Principal component analysis

Principal component analysis (PCA) is a popular technique for analyzing large datasets containing a high number of dimensions/features per observation, increasing the interpretability of data while preserving the maximum amount of information, and enabling the visualization of multidimensional data. Formally, PCA is a statistical technique for reducing the dimensionality of a dataset. This is accomplished by linearly transforming the data into a new coordinate system where (most of) the variation in the data can be described with fewer dimensions than the initial data.

Correlation

In statistics, correlation or dependence is any statistical relationship, whether causal or not, between two random variables or bivariate data. Although in the broadest sense, "correlation" may indicate any type of association, in statistics it usually refers to the degree to which a pair of variables are linearly related. Familiar examples of dependent phenomena include the correlation between the height of parents and their offspring, and the correlation between the price of a good and the quantity the consumers are willing to purchase, as it is depicted in the so-called demand curve.

Feature selection

Feature selection is the process of selecting a subset of relevant features (variables, predictors) for use in model construction. Stylometry and DNA microarray analysis are two cases where feature selection is used. It should be distinguished from feature extraction. Feature selection techniques are used for several reasons: simplification of models to make them easier to interpret by researchers/users, shorter training times, to avoid the curse of dimensionality, improve data's compatibility with a learning model class, encode inherent symmetries present in the input space.

Feature engineering

Feature engineering or feature extraction or feature discovery is the process of extracting features (characteristics, properties, attributes) from raw data. Due to deep learning networks, such as convolutional neural networks, that are able to learn it by itself, domain-specific- based feature engineering has become obsolete for vision and speech processing.

Feature (machine learning)

In machine learning and pattern recognition, a feature is an individual measurable property or characteristic of a phenomenon. Choosing informative, discriminating and independent features is a crucial element of effective algorithms in pattern recognition, classification and regression. Features are usually numeric, but structural features such as strings and graphs are used in syntactic pattern recognition. The concept of "feature" is related to that of explanatory variable used in statistical techniques such as linear regression.

Related lectures (35)

Principal Component Analysis: Dimensionality Reduction

Covers Principal Component Analysis for dimensionality reduction, exploring its applications, limitations, and importance of choosing the right components.

Maximum Likelihood: Inference and Model Comparison

Explores maximum likelihood inference, model selection, and comparing models using likelihood ratios.

Applied Machine Learning

Introduces applied machine learning concepts such as data collection, feature engineering, model selection, and performance evaluation metrics.

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

Applied Machine Learning: Features and Models