Attacking Machine Learning: On the Security and Privacy of Neural Networks
Nicholas Carlini, Research Scientist, Google
Despite significant successes, machine learning has serious security and privacy concerns. This talk will examine two of these. First, how adversarial examples can be used to fool state-of-the-art vision classifiers (to, e.g., make self-driving cars incorrectly classify road signs). Second, how to extract private training data out of a trained neural network.Learning Objectives:1: Recognize the potential impact of adversarial examples for attacking neural network classifiers.2: Understand how sensitive training data can be leaked through exposing APIs to pre-trained models.3: Know when you need to deploy defenses to counter these new threats in the machine learning age.Pre-Requisites:Understanding of threats on traditional classifiers (e.g., spam or malware systems), evasion attacks, and privacy, as well as the basics of machine learning.
Видео Attacking Machine Learning: On the Security and Privacy of Neural Networks канала RSA Conference
Despite significant successes, machine learning has serious security and privacy concerns. This talk will examine two of these. First, how adversarial examples can be used to fool state-of-the-art vision classifiers (to, e.g., make self-driving cars incorrectly classify road signs). Second, how to extract private training data out of a trained neural network.Learning Objectives:1: Recognize the potential impact of adversarial examples for attacking neural network classifiers.2: Understand how sensitive training data can be leaked through exposing APIs to pre-trained models.3: Know when you need to deploy defenses to counter these new threats in the machine learning age.Pre-Requisites:Understanding of threats on traditional classifiers (e.g., spam or malware systems), evasion attacks, and privacy, as well as the basics of machine learning.
Видео Attacking Machine Learning: On the Security and Privacy of Neural Networks канала RSA Conference
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
On Evaluating Adversarial Robustness
Security and Privacy of Machine Learning
AI & ML in Cyber Security - Why Algorithms are Dangerous
Adversarial Attacks on Neural Networks - Bug or Feature?
The Five Most Dangerous New Attack Techniques and How to Counter Them
Lecture 16 | Adversarial Examples and Adversarial Training
Spiking Neural Networks for More Efficient AI Algorithms
Machine Learning: Living in the Age of AI | A WIRED Film
Trustworthy AI: Adversarially (non-)Robust ML | Nicholas Carlini Google AI | AI FOR GOOD DISCOVERY
The Deep End of Deep Learning | Hugo Larochelle | TEDxBoston
Webinar - Hacking AI: Security & Privacy of Machine Learning Models
How to Build an Effective API Security Strategy
Adversarial Machine Learning explained! | With examples.
Yang Zhang (CISPA), Quantifying Privacy Risks of Machine Learning Models
ML in Production: Serverless and Painless - Oliver Gindele, PhD | ODSC Europe 2019
Adversarial Examples Are Not Bugs, They Are Features
Vitaly Shmatikov, How to Salvage Federated Learning
Recent Progress in Adversarial Robustness of AI Models: Attacks, Defenses, and Certification
Building Neural Network Models That Can Reason