Details

Not with a Bug, But with a Sticker


Not with a Bug, But with a Sticker

Attacks on Machine Learning Systems and What To Do About Them
1. Aufl.

von: Ram Shankar Siva Kumar, Hyrum Anderson, Bruce Schneier

18,99 €

Verlag: Wiley
Format: EPUB
Veröffentl.: 31.03.2023
ISBN/EAN: 9781119883999
Sprache: englisch
Anzahl Seiten: 208

DRM-geschütztes eBook, Sie benötigen z.B. Adobe Digital Editions und eine Adobe ID zum Lesen.

Beschreibungen

<p><b>A robust and engaging account of the single greatest threat faced by AI and ML systems</b> <p>In <i>Not With A Bug, But With A Sticker: Attacks on Machine Learning Systems and What To Do About Them</i>, 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. <p>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. <p>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. <p>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, <i>Not With A Bug, But With A Sticker </i>is a warning—albeit an entertaining and engaging one—we should all heed. <p>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. <p>The authors are donating the proceeds from this book to two charities: Black in AI and Bountiful Children’s Foundation.
<p>Foreword xv</p> <p>Introduction xix</p> <p><b>Chapter 1: Do You Want to Be Part of the Future? 1</b></p> <p>Business at the Speed of AI 2</p> <p>Follow Me, Follow Me 4</p> <p>In AI, We Overtrust 6</p> <p>Area 52 Ramblings 10</p> <p>I’ll Do It 12</p> <p>Adversarial Attacks Are Happening 16</p> <p>ML Systems Don’t Jiggle-Jiggle; They Fold 19</p> <p>Never Tell Me the Odds 22</p> <p>AI’s Achilles’ Heel 25</p> <p><b>Chapter 2: Salt, Tape, and Split-Second Phantoms 29</b></p> <p>Challenge Accepted 30</p> <p>When Expectation Meets Reality 35</p> <p>Color Me Blind 39</p> <p>Translation Fails 42</p> <p>Attacking AI Systems via Fails 44</p> <p>Autonomous Trap 001 48</p> <p>Common Corruption 51</p> <p><b>Chapter 3: Subtle, Specific, and Ever-Present 55</b></p> <p>Intriguing Properties of Neural Networks 57</p> <p>They Are Everywhere 60</p> <p>Research Disciplines Collide 62</p> <p>Blame Canada 66</p> <p>The Intelligent Wiggle-Jiggle 71</p> <p>Bargain-Bin Models Will Do 75</p> <p>For Whom the Adversarial Example Bell Tolls 79</p> <p><b>Chapter 4: Here’s Something I Found on the Web 85</b></p> <p>Bad Data = Big Problem 87</p> <p>Your AI Is Powered by Ghost Workers 88</p> <p>Your AI Is Powered by Vampire Novels 91</p> <p>Don’t Believe Everything You Read on the Internet 94</p> <p>Poisoning the Well 96</p> <p>The Higher You Climb, the Harder You Fall 104</p> <p><b>Chapter 5: Can You Keep a Secret? 107</b></p> <p>Why Is Defending Against Adversarial Attacks Hard? 108</p> <p>Masking Is Important 111</p> <p>Because It Is Possible 115</p> <p>Masking Alone Is Not Good Enough 118</p> <p>An Average Concerned Citizen 119</p> <p>Security by Obscurity Has Limited Benefit 124</p> <p>The Opportunity Is Great; the Threat Is Real; the Approach Must Be Bold 125</p> <p>Swiss Cheese 130</p> <p><b>Chapter 6: Sailing for Adventure on the Deep Blue Sea 133</b></p> <p>Why Be Securin’ AI Systems So Blasted Hard? An Economics Perspective, Me Hearties! 136</p> <p>Tis a Sign, Me Mateys 141</p> <p>Here Be the Most Crucial AI Law Ye’ve Nary Heard Tell Of! 144</p> <p>Lies, Accursed Lies, and Explanations! 146</p> <p>No Free Grub 148</p> <p>Whatcha measure be whatcha get! 151</p> <p>Who Be Reapin’ the Benefits? 153</p> <p>Cargo Cult Science 155</p> <p><b>Chapter 7: The Big One 159</b></p> <p>This Looks Futuristic 161</p> <p>By All Means, Move at a Glacial Pace; You Know How That Thrills Me 163</p> <p>Waiting for the Big One 166</p> <p>Software, All the Way Down 169</p> <p>The Aftermath 172</p> <p>Race to AI Safety 173</p> <p>Happy Story 176</p> <p>In Medias Res 178</p> <p>Big-Picture Questions 181</p> <p>Acknowledgments 185</p> <p>Index 189</p>
<p><b>Ram Shankar Siva Kumar</b> is Data Cowboy at Microsoft, working on the intersection of machine learning and security. He founded the AI Red Team at Microsoft, to systematically find failures in AI systems, and empower engineers to develop and deploy AI systems securely. His work has been featured in popular media including <i>Harvard Business Review</i>, <i>Bloomberg</i>, <i>Wired</i>, <i>VentureBeat</i>, <i>Business Insider</i>, and <i>GeekWire.</i> He is part of the Technical Advisory Board at University of Washington and affiliate at Berkman Klein Center at Harvard University.</p> <p><b>Dr. Hyrum Anderson</b> is Distinguished Engineer at Robust Intelligence. Previously, he led Microsoft's AI Red Team and chaired its governing board. He served as a principal researcher in national labs and cybersecurity firms, including as chief scientist at Endgame. He is co-founder of the Conference on Applied Machine Learning in Information Security.</p>
<p>"As we enter an era of unprecedented growth of the capacity and power of machine learning and large AI platforms, the new benefits offered by such systems will be met with a corresponding expansion of the surface area for potential risks. NOT WITH A BUG, BUT WITH A STICKER is essential reading not just for those in technology or public policy, but for anyone who wants to better understand how profoundly AI and ML will shape our shared societal future." —<i>Kevin Scott, Chief Technology Officer, Microsoft</i></p> <p>"Like any new technology, the great potential benefits of AI/ML come with a host of potential downsides. We have only begun to understand these risks, but NOT WITH A BUG, BUT WITH A STICKER shines a light on the important challenges associated with securing AI/ML systems. Siva Kumar and Anderson are uniquely qualified to identify these challenges given their decades of experience and research on the topic. Further, their writing is both accessible and enjoyable despite going into deep technical details. As AI/ML systems increasingly pervade everyday life, the lessons they impart are critical for everyone from casual technology users to corporate leaders to policy makers." —<i>Frank Nagle, Asst. Professor of Business Administration, Harvard University</i></p> <p>"A reality of the digital age is that every innovation contains security risk, and every security risk attracts an attacker. Ram Shankar Siva Kumar and Hyrum Anderson fire a much-needed warning flare in NOT WITH A BUG, BUT WITH A STICKER: we over-trust artificial intelligence at our peril. Every leader and policymaker should read this compelling and persuasive book." —<i>Nate Fick, New York Times bestselling author, and former CEO of the cybersecurity firm Endgame</i></p> <p>"The intersection of technology and national security has always been a story of tension between attack and defense. With AI, the speed of attack has accelerated dramatically, while defense has not kept pace. This excellent, lively analysis shows how AI's limitations and vulnerabilities can jeopardize national security. Most importantly, Siva Kumar and Anderson provide concrete, feasible recommendations for taking steps today to bolster defenses against the certainty of pervasive adversarial AI attacks." —<i>Lt. Gen. John (Jack) N.T. Shanahan, USAF (Ret.); inaugural Director, U.S. Department of Defense Joint AI Center (JAIC)</i></p> <p>"This is such a timely and readable book—the authors do a fantastic job of explaining complex topics and modern research in plain language with plenty of references for further exploration. AI and ML have immense utility and potential, and it's critical for security teams, builders, and operators to understand the sharp edges and pitfalls along with the benefits." —<i>Jason Chan, Former Information Security Leader, Netflix</i></p> <p>"NOT WITH A BUG, BUT WITH A STICKER is an informative, engaging, and fun foray into how AI can be easily fooled. An excellent read for both technical and nontechnical readers, the book provides a global perspective on what's happening today and empowers the reader with tools to make informed decisions that impact tomorrow. This book focuses on both technical and human interventions to ensure the secure use of AI systems." —<i>Dr. Rumman Chowdhury, Founder, Bias Buccaneers</i></p> <p>"Siva Kumar and Anderson skillfully deliver a message that AI practitioners, decision-makers, and users of AI systems must hear: our AI systems are not safe, and the blind trust placed into AI is putting our nation at risk. With ample background, anecdotes, and data, the authors make the science accessible, update the current academic discourse, and highlight the implications for public policy. No matter whether you work in the field or are an AI enthusiast, this book is a must-read." —<i>Sven Krasser, Senior Vice President and Chief Scientist, Crowdstrike</i></p> <p>"As AI systems get more capable and are deployed in a wider range of contexts, more and more people will try to break them, with wide-ranging consequences. Not with a Bug, but with a Sticker provides a timely overview of this emerging risk landscape and what can be done about it." —<i>Miles Brundage, Head of Policy Research, OpenAI</i></p> <p>"As AI becomes infused into all computer systems, from social networks to business-critical infrastructure and defense systems, the security of those systems depends on the security of the AI they use. This book presents the unique risks and considerations of AI with engaging stories and insightful examples. It is a wake-up call to security professionals and organizations adopting and developing AI." —<i>Mark Russinovich, Azure CTO and Technical Fellow, Microsoft</i></p> <p>"'The threat is not hypothetical'—a quote used by the authors to open the book remains top of mind as you come to the conclusion of this brilliant work. In the final paragraphs, one thing is clear: there is a call to action, and we must act 'hand in hand' on securing AI systems with haste." —<i>Vijay Bolina, Chief Information Security Officer, DeepMind</i></p> <p>"Siva Kumar and Anderson take you on a wild ride uncovering the victories and triumphs of AI/ML. This should be required reading to become AI/ML literate in the field." —<i>David Brumley, Professor of ECE and CS, Carnegie Mellon University</i></p> <p>"Trust, in ways both good and bad, is emerging as a critical aspect of the relationships we are coming to have with AI. NOT WITH A BUG, BUT WITH A STICKER is an eye-opening book that will change the way you think about the systems that pervade our world—and its lessons should be taken to heart by all who build them." —<i>Brian Christian, author of The Alignment Problem</i></p> <p>"NOT WITH A BUG, BUT WITH A STICKER is a rare inside look at the absurd AI quirks that are keeping security experts awake at night. I'm going to start bringing up examples from this book immediately." —<i>Janelle Shane, author of You Look Like A Thing And I Love You: How AI Works And Why It's Making The World A Weirder Place</i></p> <p>"At last—and not a moment too soon—a book that in plain language describes the distinct and deep issues of securing now-ubiquitous machine learning tools. Whether you're looking to deploy them in your own domain, or simply among the billions of people now subject to them, this is a vital read." —<i>Jonathan Zittrain, George Bemis Professor of International Law and Professor of Computer Science, Harvard University</i></p> <p>"We are fast entering a world of powerful but brittle AI systems, one where failures can result in catastrophic consequences. Siva Kumar and Anderson have written an essential guide for understanding the unique —and troubling —failure modes of AI systems today. Through easily accessible examples and anecdotes, they break down the problems of machine learning systems and how society can address them to build a safer world." —<i>Paul Scharre, author of Four Battlegrounds and Army of None</i></p> <p>"Siva Kumar and Anderson are veterans at the intersection of machine learning and security, and in this work, they delight us with a guided tour across the history of this fascinating field. The book dives into why this field should become one of the top priorities for those who are developing and deploying AI systems, providing ample material that will benefit novices and pros alike. Readers of this book will earn a competitive advantage in machine learning, especially as responsibility becomes a non-negotiable aspect of fielding advanced technological systems."—<i>Abhishek Gupta, Founder and Principal Researcher, Montreal AI Ethics Institute</i></p>

Diese Produkte könnten Sie auch interessieren:

Quantifiers in Action
Quantifiers in Action
von: Antonio Badia
PDF ebook
96,29 €
Managing and Mining Uncertain Data
Managing and Mining Uncertain Data
von: Charu C. Aggarwal
PDF ebook
96,29 €