A robust and engaging account of the single greatest threat faced by AI and ML systems
In Not With A Bug, But With A Sticker: Attacks on Machine Learning Systems and What To Do About Them, a team of distinguished adversarial machine learning researchers deliver a riveting account of the most significant risk to currently deployed artificial intelligence systems: cybersecurity threats. The authors take you on a sweeping tour – from inside secretive government organizations to academic workshops at ski chalets to Google’s cafeteria – recounting how major AI systems remain vulnerable to the exploits of bad actors of all stripes.
Based on hundreds of interviews of academic researchers, policy makers, business leaders and national security experts, the authors compile the complex science of attacking AI systems with color and flourish and provide a front row seat to those who championed this change. Grounded in real world examples of previous attacks, you will learn how adversaries can upend the reliability of otherwise robust AI systems with straightforward exploits.
The steeplechase to solve this problem has already begun: Nations and organizations are aware that securing AI systems brings forth an indomitable advantage: the prize is not just to keep AI systems safe but also the ability to disrupt the competition’s AI systems.
An essential and eye-opening resource for machine learning and software engineers, policy makers and business leaders involved with artificial intelligence, and academics studying topics including cybersecurity and computer science, Not With A Bug, But With A Sticker is a warning―albeit an entertaining and engaging one―we should all heed.
How we secure our AI systems will define the next decade. The stakes have never been higher, and public attention and debate on the issue has never been scarcer.
The authors are donating the proceeds from this book to two charities: Black in AI and Bountiful Children’s Foundation.
Author(s): Ram Shankar; Siva Kumar; Hyrum Anderson
Publisher: Wiley
Year: 2023
Language: English
Pages: 231
Cover
Title Page
Copyright Page
Contents
Foreword
Introduction
Chapter 1 Do You Want to Be Partof the Future?
Business at the Speed of AI
Follow Me, Follow Me
In AI, We Overtrust
Area 52 Ramblings
I’ll Do It
Adversarial Attacks Are Happening
ML Systems Don’t Jiggle-Jiggle;They Fold
Never Tell Me the Odds
AI’s Achilles’ Heel
Chapter 2 Salt, Tape, and Split-Second Phantoms
Challenge Accepted
When Expectation Meets Reality
Color Me Blind
Translation Fails
Attacking AI Systems via Fails
Autonomous Trap 001
Common Corruption
Chapter 3 Subtle, Specific, and Ever-Present
Intriguing Properties of Neural Networks
They Are Everywhere
Research Disciplines Collide
Blame Canada
The Intelligent Wiggle-Jiggle
Bargain-Bin Models Will Do
For Whom the Adversarial Example Bell Tolls
Chapter 4 Here’s Something I Foundon the Web
Bad Data = Big Problem
Your AI Is Powered by Ghost Workers
Your AI Is Powered by Vampire Novels
Don’t Believe Everything You Read on the Internet
Poisoning the Well
The Higher You Climb, the Harder You Fall
Chapter 5 Can You Keep a Secret?
Why Is Defending Against Adversarial Attacks Hard?
Masking Is Important
Because It Is Possible
Masking Alone Is Not Good Enough
An Average Concerned Citizen
Security by Obscurity Has Limited Benefit
The Opportunity Is Great; the Threat Is Real; the Approach Must Be Bold
Swiss Cheese
Chapter 6 Sailing for Adventure on the Deep Blue Sea
Why Be Securin’ AI Systems So Blasted Hard? An Economics Perspective, Me Hearties!
Tis a Sign, Me Mateys
Here Be the Most Crucial AI Law Ye’ve Nary Heard Tell Of!
Lies, Accursed Lies, and Explanations!
No Free Grub
Whatcha measure be whatcha get!
Who Be Reapin’ the Benefits?
Cargo Cult Science
Chapter 7 The Big One
This Looks Futuristic
By All Means, Move at a Glacial Pace; You Know How That Thrills Me
Waiting for the Big One
Software, All the Way Down
The Aftermath
Race to AI Safety
Happy Story
In Medias Res
Appendix A Big-Picture Questions
Acknowledgments
Index
EULA
