Adversarial Attacks Courses and Certifications

Domain Adaptation with Invariant Representation Learning - What Transformations to Learn?

Explore domain adaptation in machine learning, focusing on invariant representation learning and its challenges. Learn about novel techniques for optimal feature mapping across domains.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Optimizing for Interpretability in Deep Neural Networks - Mike Wu

Explore techniques for making deep neural networks more interpretable through regularization, focusing on medical applications in critical care and HIV treatment. Insights on balancing model performance with human-understandable decision processes.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Analyzing and Exposing Vulnerabilities in Language Models - Session 131

Delve into advanced research on language model vulnerabilities, exploring novel adversarial attack methods and gender bias analysis while discovering practical approaches to enhance AI trustworthiness and fairness.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Alexander Amini;  MIT

Neurosymbolic AI

2 ratings

Explore neurosymbolic AI, combining deep learning and symbolic reasoning to address limitations in current AI systems. Learn about out-of-distribution performance, adversarial examples, and advantages of hybrid approaches.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Navigating AI/ML Challenges in Medical Software Development - 11.6

Explore AI/ML challenges in medical software development, covering risk assessment, training data quality, and robust system design for clinical applications.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Artificial Intelligence: A Guide for Thinking Humans

Explore AI's achievements, failures, and ethical implications with researcher Melanie Mitchell. Gain insights into machine learning, self-driving cars, and the challenges of imbuing computers with human-like qualities.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Advanced Computer Vision - Spring 2021

Dive into adversarial machine learning, explainable AI, and robust neural network architectures through cutting-edge research papers and advanced computer vision techniques.

• YouTube
• 12 hours 40 minutes
• Self-Paced
• Free Video

Yannic Kilcher

End-to-End Adversarial Text-to-Speech - Paper Explained

Explore end-to-end adversarial text-to-speech synthesis, tackling alignment challenges and producing high-quality audio directly from text input using innovative neural network architectures and training techniques.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Yannic Kilcher

Manifold Mixup: Better Representations by Interpolating Hidden States

Explore Manifold Mixup, a regularization technique that improves neural network performance by interpolating hidden representations, leading to smoother decision boundaries and more robust predictions.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Yannic Kilcher

Adversarial Examples Are Not Bugs, They Are Features

Explore the concept of adversarial examples in machine learning, their origins, and implications for AI robustness and human-AI alignment.

• YouTube
• 40 minutes
• Self-Paced
• Free Video

Yannic Kilcher

How Apple Scans Your Phone and How to Evade It - NeuralHash CSAM Detection Algorithm Explained

Detailed exploration of Apple's CSAM detection system, analyzing its technical aspects, privacy measures, and potential weaknesses. Covers NeuralHash, private set intersection, and threshold secret sharing.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Yannic Kilcher

The Dimpled Manifold Model of Adversarial Examples in Machine Learning - Research Paper Explained

Explores the Dimpled Manifold Model to explain adversarial examples in machine learning, challenging existing theories and providing experimental evidence for a new perspective on neural network vulnerabilities.

• YouTube
• 1 hour 14 minutes
• Self-Paced
• Free Video

Alexander Amini;  MIT

Deep Learning New Frontiers

Explore deep learning limitations and new frontiers, including expressivity, generalization, failure modes, uncertainty, adversarial attacks, and emerging areas like graph learning and AutoML.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Alexander Amini;  MIT

MIT 6.S191 - Deep Learning Limitations and New Frontiers

Explore deep learning limitations, adversarial attacks, uncertainty quantification, and AutoML in this lecture. Gain insights into neural network challenges and emerging frontiers in AI research.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

Alexander Amini;  MIT

Deep Learning Limitations and New Frontiers

Explore deep learning limitations, new frontiers, and advancements in AI, including uncertainty estimation, adversarial attacks, and meta-learning, with insights on future developments and applications.

• YouTube
• 32 minutes
• Self-Paced
• Free Video