Machine Learning Security: Adversarial Attacks and Biases

Description

This lecture covers the basics of machine learning security, including the risks of model stealing, adversarial attacks altering model outputs, and biases in AI systems. It explores the challenges of protecting models against attacks and mitigating biases to ensure fair and accurate predictions.

Official source

https://mediaspace.epfl.ch/media/0_mi525y1f

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (40)

Related concepts (49)

Algorithmic bias

Algorithmic bias describes systematic and repeatable errors in a computer system that create "unfair" outcomes, such as "privileging" one category over another in ways different from the intended function of the algorithm. Bias can emerge from many factors, including but not limited to the design of the algorithm or the unintended or unanticipated use or decisions relating to the way data is coded, collected, selected or used to train the algorithm. For example, algorithmic bias has been observed in search engine results and social media platforms.

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

AI alignment

In the field of artificial intelligence (AI), AI alignment research aims to steer AI systems towards humans' intended goals, preferences, or ethical principles. An AI system is considered aligned if it advances the intended objectives. A misaligned AI system pursues some objectives, but not the intended ones. It can be challenging for AI designers to align an AI system because it can be difficult for them to specify the full range of desired and undesired behaviors.

Cognitive bias mitigation

Cognitive bias mitigation is the prevention and reduction of the negative effects of cognitive biases – unconscious, automatic influences on human judgment and decision making that reliably produce reasoning errors. Coherent, comprehensive theories of cognitive bias mitigation are lacking. This article describes debiasing tools, methods, proposals and other initiatives, in academic and professional disciplines concerned with the efficacy of human reasoning, associated with the concept of cognitive bias mitigation; most address mitigation tacitly rather than explicitly.

Ethics of artificial intelligence

The ethics of artificial intelligence is the branch of the ethics of technology specific to artificially intelligent systems. It is sometimes divided into a concern with the moral behavior of humans as they design, make, use and treat artificially intelligent systems, and a concern with the behavior of machines, in machine ethics. Robot ethics The term "robot ethics" (sometimes "roboethics") refers to the morality of how humans design, construct, use and treat robots. Robot ethics intersect with the ethics of AI.