Lecture

Machine Learning and Privacy

Graph Chat

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.

In course

CS-523: Advanced topics on privacy enhancing technologies

This advanced course will provide students with the knowledge to tackle the design of privacy-preserving ICT systems. Students will learn about existing technologies to prect privacy, and how to evaluate the protection they provide. ...

Description

This lecture covers the fundamental concepts of machine learning and privacy, including the training process, privacy concerns, privacy attacks, and the implications of collaborative machine learning. It delves into topics such as membership inference attacks, model inversion, and gradient inversion, highlighting the privacy risks associated with trained machine learning models. The instructor emphasizes the importance of understanding the privacy implications of machine learning models and the potential risks of data leakage and privacy attacks.

Instructors (2)

Carmela González Troncoso

SPRING Lab Our research focuses on building secure and privacy-preserving systems. We aim to develop tools and methodologies to help engineers embedding strong security and privacy guarantees in their designs, as well as techniques that help them to systematically quantifying the information that an adversary can infer from data she may have access to.More information about our activities here: https://spring.epfl.ch/ Teaching & PhD PhD Students Saiid El Hajj Chehade, Eric Jollès, Christian Knabenhans, Boy

Alessandro Chiesa

Alessandro Chiesa is a faculty member in computer science. He conducts research in complexity theory, cryptography, and security, with a focus on the theoretical foundations and practical implementations of cryptographic proofs that are short and easy to verify. He is a co-author of several zkSNARK libraries, and is a co-inventor of the Zerocash protocol. He has co-founded Zcash and StarkWare Industries. He is a recipient of a Sloan Research Fellowship (2021), an Okawa Foundation Research Grant (2020), and Google Faculty Research Awards (2018 and 2017). He was included in MIT Technology Review's "35 Innovators Under 35" list in 2018.

Official source

Related concepts (31)

Privacy law

Privacy law is the body of law that deals with the regulating, storing, and using of personally identifiable information, personal healthcare information, and financial information of individuals, which can be collected by governments, public or private organisations, or other individuals. It also applies in the commercial sector to things like trade secrets and the liability that directors, officers, and employees have when handing sensitive information.

Right to privacy

The right to privacy is an element of various legal traditions that intends to restrain governmental and private actions that threaten the privacy of individuals. Over 150 national constitutions mention the right to privacy. On 10 December 1948, the United Nations General Assembly adopted the Universal Declaration of Human Rights (UDHR), originally written to guarantee individual rights of everyone everywhere; while right to privacy does not appear in the document, many interpret this through Article 12, which states: "No one shall be subjected to arbitrary interference with his privacy, family, home or correspondence, nor to attacks upon his honour and reputation.

Inversion (meteorology)

In meteorology, an inversion is a deviation from the normal change of an atmospheric property with altitude. It almost always refers to an inversion of the air temperature lapse rate, in which case it is called a temperature inversion. Normally, air temperature decreases with an increase in altitude, but during an inversion warmer air is held above cooler air. An inversion traps air pollution, such as smog, close to the ground. An inversion can also suppress convection by acting as a "cap".

Internet privacy

Internet privacy involves the right or mandate of personal privacy concerning the storage, re-purposing, provision to third parties, and display of information pertaining to oneself via the Internet. Internet privacy is a subset of data privacy. Privacy concerns have been articulated from the beginnings of large-scale computer sharing and especially relate to mass surveillance enabled by the emergence of computer technologies. Privacy can entail either personally identifiable information (PII) or non-PII information such as a site visitor's behaviour on a website.

Gradient descent

In mathematics, gradient descent (also often called steepest descent) is a iterative optimization algorithm for finding a local minimum of a differentiable function. The idea is to take repeated steps in the opposite direction of the gradient (or approximate gradient) of the function at the current point, because this is the direction of steepest descent. Conversely, stepping in the direction of the gradient will lead to a local maximum of that function; the procedure is then known as gradient ascent.

Related lectures (64)

Machine Learning and Privacy

Delves into Differential Privacy trade-offs, disparate impact, and machine learning-based privacy attacks.

Machine Learning and Privacy

Explores Federated Machine Learning and Differential Privacy in Machine Learning, discussing attacks, defenses, and challenges.

Media Security Standards

Explores the definition of media security standards and the standardization of a framework rather than a specific security tool.

Privacy Technologies and Data Protection

Explores privacy technologies, data protection, surveillance risks, and Privacy Enhancing Technologies for social and institutional privacy.

Privacy Engineering: Design Principles and SwissCovid Case Study

Explores Privacy by Design principles, data minimization, trust minimization, and the SwissCovid app case study.

Related concepts (31)

Privacy law

Right to privacy

Inversion (meteorology)

Internet privacy

Gradient descent