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

Lecture

Threat Modeling: Adversarial Examples and Backdoors

Description

This lecture covers threat modeling in the context of deep learning for autonomous vehicles, focusing on adversarial examples and backdoors. The instructor discusses attacker's goals, defending strategies, and the challenges of ensuring security in machine learning models.

Official source

Related concepts (23)

Autonomous robot

An autonomous robot is a robot that acts without recourse to human control. The first autonomous robots environment were known as Elmer and Elsie, which were constructed in the late 1940s by W. Grey Walter. They were the first robots in history that were programmed to "think" the way biological brains do and meant to have free will. Elmer and Elsie were often labeled as tortoises because of how they were shaped and the manner in which they moved. They were capable of phototaxis which is the movement that occurs in response to light stimulus.

Unmanned ground vehicle

An unmanned ground vehicle (UGV) is a vehicle that operates while in contact with the ground and without an onboard human presence. UGVs can be used for many applications where it may be inconvenient, dangerous, or impossible to have a human operator present. Generally, the vehicle will have a set of sensors to observe the environment, and will either autonomously make decisions about its behavior or pass the information to a human operator at a different location who will control the vehicle through teleoperation.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

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.

Generative adversarial network

A generative adversarial network (GAN) is a class of machine learning framework and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss. Given a training set, this technique learns to generate new data with the same statistics as the training set.

Related lectures (36)

Generative Models: Trajectory Forecasting

Explores generative models for trajectory forecasting in autonomous vehicles, including discriminative vs generative models, VAES, GANS, and case studies.

Deep Learning for Autonomous Vehicles: Predictive Models

Explores predictive models and trackers for autonomous vehicles, covering object detection, tracking challenges, neural network-based tracking, and 3D pedestrian localization.

Deep Learning for Autonomous Vehicles: Learning

Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.

Neural Networks Optimization

Explores neural networks optimization, including backpropagation, batch normalization, weight initialization, and hyperparameter search strategies.

Perception: Data-Driven Approaches