in Machine Learning Nicholas Carlini University of California, - PowerPoint PPT Presentation

Sep 30, 2022 •331 likes •892 views

Security (and Privacy) in Machine Learning Nicholas Carlini University of California, Berkeley (now Google Brain) This talk: neural networks Machine learning is amazing But there's a catch Understandability This talk: Discuss security

Security (and Privacy)   in Machine Learning Nicholas Carlini University of California, Berkeley (now Google Brain)
This talk: neural networks
Machine learning is amazing But there's a catch
Understandability
This talk: Discuss security & privacy problems being studied in the research community
What this talk is not
What this talk is not
What this talk is
What are the security problems in machine learning today?
French Bulldog (95%)
Old English Sheepdog (83%)
Greater Swiss Mountain Dog (78%)
Siberian Husky (81%)
Great Dane (67%)
Beagle (96%)
Guacamole (99.99%)
Golden   Retriever (96%)
Guacamole (99.99%)
These phenomena are known as adversarial examples B. Biggio, I. Corona, D. Maiorca, B. Nelson, N. Srndic, P. Laskov, G. Giacinto, and F. Roli. Evasion attacks against machine learning at test time. 2013. C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intriguing properties of neural networks. ICLR 2014. I. Goodfellow, J. Shlens, and C. Szegedy. Explaining and harnessing adversarial examples. 2014.
What does this have to do with voice?
We use these same classification approaches for speech recognition.
Attacks on Android, circa 2015
State-of-the-art in 2015
It's been three years. Can we do better?
Feynman Algorithm 1. Write down the problem. 2. Think very hard. 3. Write down the answer.
Mozilla's DeepSpeech
Mozilla's DeepSpeech transcribes this as "most of them were staring   quietly at the big table"
Mozilla's DeepSpeech transcribes this as "most of them were staring   quietly at the big table"
[adversarial]
"It was the best of times, it was the worst of times, it was the age of wisdom, it was the age of foolishness, it was the epoch of belief, it was the epoch of incredulity"
Why is this so much stealthier?
It works on music, too DeepSpeech transcribes "speech can be embedded in music"
And can "hide" speech DeepSpeech does not hear any speech in this audio sample
That's a lot of problems Do you have any solutions?
Sorry, no. This is an active area of research. Ask me again in two years.
Yes, machine learning gives amazing results
However, there are   also significant   vulnerabilities Guacamole (99%)
Questions? More Details: https://nicholas.carlini.com

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

An Exercise in An Exercise in Machine Learning Machine Learning

An Exercise in An Exercise in Machine Learning Machine Learning http://www.cs.iastate.edu/~cs573x/bbsilab.html Machine Learning Software Preparing Data Building Classifiers Interpreting Results Machine Learning Software

496 views • 26 slides

Machine Learning By Alex Scarlatos What is Machine Learning? Machine Learning is the process by

Machine Learning By Alex Scarlatos What is Machine Learning? Machine Learning is the process by which computers can be trained through observation, rather than being explicitly programmed. Basically, a program is given input and adjusts its

556 views • 17 slides

Machine Learning: Study of algorithms that improve their performance P at some task T

Machine Learning 10-601 Tom M. Mitchell Machine Learning Department Carnegie Mellon University January 12, 2015 Today: Readings: What is machine learning? The Discipline of ML Decision tree learning Mitchell, Chapter 3

872 views • 29 slides

Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning Pipeline in Classification Tasks A set of hand-designed audio features are selected

398 views • 26 slides

CS 335 Machine Learning What is Machine Learning? Dan Sheldon Spring 2019 What is Machine

1/22/19 CS 335 Machine Learning What is Machine Learning? Dan Sheldon Spring 2019 What is Machine Learning? A Simple Task: Recognize Obama How do you program a computer to Recognize faces? Recommend movies? Decide which web

581 views • 5 slides

Machine Learning Machine Learning: algorithms that use experience to improve their

Machine Learning Machine Learning: algorithms that use experience to improve their performance We use machine learning in situations where it is very challenging (or impossible) to define the rules by hand: e.g. face detection

1.04k views • 28 slides

Introduction to Machine Learning COMPSCI 371D Machine Learning COMPSCI 371D Machine

Introduction to Machine Learning COMPSCI 371D Machine Learning COMPSCI 371D Machine Learning Introduction to Machine Learning 1 / 12 Outline 1 Nearest Neighbor Prediction 2 Complexity Considerations 3 The Voronoi Diagram 4 Overfitting

564 views • 12 slides

1 Why Study Machine Learning? Why Study Machine Learning? Cognitive Science The Time is Ripe

What is Learning? Herbert Simon: Learning is any process by which a system improves performance from CS 391L: Machine Learning experience. Introduction What is the task? Classification Problem solving / planning /

603 views • 6 slides

MACHINE LEARNING, STATISTICAL LEARNING AND PARALLEL COMPUTING INTRODUCTION VS MACHINE LEARNING

JACOPO DI IORIO, MATTEO FONTANA, DANIELE OCCHIUTO, CLAUDIA VOLPETTI MACHINE LEARNING, STATISTICAL LEARNING AND PARALLEL COMPUTING INTRODUCTION VS MACHINE LEARNING STATISTICAL LEARNING Separate evolutions, but with shared methodologies MERGE

565 views • 55 slides

Apache PredictionIO End-to-End Machine Learning Server with Apache Spark What is Machine

Apache PredictionIO End-to-End Machine Learning Server with Apache Spark What is Machine Learning? What is Machine Learning? Examples of machine learning applications: Facial recognition software E-mail spam detectors Automated

302 views • 17 slides

Machine Learning 11 AI Slides (6e) c Lin Zuoquan@PKU 1998-2020 11 1 11 Machine Learning

Machine Learning 11 AI Slides (6e) c Lin Zuoquan@PKU 1998-2020 11 1 11 Machine Learning 11.1 Learning agents 11.2 Inductive learning 11.3 Deep learning 11.4 Statistical learning 11.5 Reinforcement learning 11.6 Transfer learning

1.7k views • 159 slides

Deep Learning: Intro Juhan Nam Review of Traditional Machine Learning The traditional machine

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Deep Learning: Intro Juhan Nam Review of Traditional Machine Learning The traditional machine learning pipeline Temporal Frame-level Unsupervised Classifier Summary

613 views • 27 slides

Machine Learning for Auto Optimization What is Machine Learning? Definition: Machine

Machine Learning for Auto Optimization What is Machine Learning? Definition: Machine learning refers to any system where the performance of a machine in performing a task improves by gaining more experience in performing that task .

394 views • 27 slides

MACHINE LEARNING kernels 1 MACHINE LEARNING 2012 MACHINE LEARNING Kernels: Intuition How

MACHINE LEARNING 2012 MACHINE LEARNING MACHINE LEARNING kernels 1 MACHINE LEARNING 2012 MACHINE LEARNING Kernels: Intuition How to separate the red class from the grey class? x 2 360 r x 1 Polar coordinates Data

1.04k views • 44 slides

BBM406 Fundamentals of Machine Learning Lecture 2: Machine Learning by Examples, Nearest

photo:@rewardyfahmi // Unsplash BBM406 Fundamentals of Machine Learning Lecture 2: Machine Learning by Examples, Nearest Neighbor Classifier Aykut Erdem // Hacettepe University // Fall 2019 When Do We Use Machine Learning? ML is

1.33k views • 110 slides

Machine Learning Modeling and Learning 15-110 Monday 4/13 Learning Goals Given a

Machine Learning Modeling and Learning 15-110 Monday 4/13 Learning Goals Given a dataset, identify features which may help predict information about the data Identify common types of machine learning algorithms 2 Machine

553 views • 27 slides

Information Resources For 21 st Century Crop Production Decisions Illinois Corn Prices

Information Resources For 21 st Century Crop Production Decisions Illinois Corn Prices 2000-2008 Illinois Soybean Prices 2000-2008 Central Illinois Corn & Soybean Prices Crop Input CostsCentral Illinois 100 90 80 $ Per Acre

1.16k views • 95 slides

Introductory Course for Commercial Dog Breeders Part 1: Introduction to APHIS Animal Care and

Introductory Course for Commercial Dog Breeders Part 1: Introduction to APHIS Animal Care and the Regulatory Process Learning Objectives By the end of this unit, you should be able to: 1. Briefly describe how USDA APHIS Animal Care is

681 views • 55 slides

EMBEDDED RUST ON THE BEAGLEBOARD X15 MEETING EMBEDDED Jonathan Pallant 14 November 2018

EMBEDDED RUST ON THE BEAGLEBOARD X15 MEETING EMBEDDED Jonathan Pallant 14 November 2018 EMBEDDED-P-006 v1.4 OUR LOCATIONS CAMBRIDGE BOSTON SINGAPORE SEATTLE SAN FRANCISCO 14 November 2018 2 EMBEDDED-P-006 v1.4 What is Rust?

389 views • 21 slides

CS 103: Representation Learning, Information Theory and Control Lecture 4, Feb 1, 2019 Seen last

CS 103: Representation Learning, Information Theory and Control Lecture 4, Feb 1, 2019 Seen last time 1. What is a nuisance for a task? 2. Invariance, equivariance, canonization 3. A linear transformation is group equivariant if and only if it is

418 views • 13 slides

ANGSD Analysis of Next Generation Sequencing Data Anders Albrechtsen Why ANGSD? Focus To

ANGSD Analysis of Next Generation Sequencing Data Anders Albrechtsen Why ANGSD? Focus To perform population or medical genetic analysis on NGS data while taking uncertainly into account even for low depth data At the time no other software

1.14k views • 16 slides

Making Automatic Theorem Provers more Versatile Simon Cruanes Veridis, Inria Nancy

Making Automatic Theorem Provers more Versatile Simon Cruanes Veridis, Inria Nancy https://cedeela.fr/~simon/ August 2017 Simon Cruanes combine all the provers! August 2017 1 / 7 ATPs usefulness ATPs are successfully applied: program

656 views • 21 slides

openPOWERLINK over Xenomai Pierre Ficheux (pierre.ficheux@smile.fr) 02/2017 OpenPOWERLINK /

openPOWERLINK over Xenomai Pierre Ficheux (pierre.ficheux@smile.fr) 02/2017 OpenPOWERLINK / Xenomai 1 $ whoami French embedded Linux developer, writer and teacher CTO @ Smile-ECS (Embedded & Connected Systems) OpenPOWERLINK /

508 views • 32 slides

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides