即将到来的AI黑客.pdfVIP

Table of Contents Introduction 1 Hacks and Hacking 2 The Ubiquity of Hacking 7 AIs Hacking Us 10 Artificial Intelligence and Robotics 11 Human-Like AIs 14 Robots Hacking Us 18 When AIs Become Hackers21 The Explainability Problem 24 Reward Hacking26 AIs as Natural Hackers 31 From Science Fiction to Reality 33 The Implications of AI Hackers36 AI Hacks and Power 39 Defending Against AI Hackers 41 Belfer Center for Science and International Affairs | Harvard Kennedy School v vi The Coming AI Hackers Introduction Artificial intelligence—AI—is an information technology. It consists of software. It runs on computers. And it is already deeply embedded into our social fabric, both in ways we understand and in ways we don’t. It will hack our society to a degree and effect unlike anything that’s come before. I mean this in two very different ways. One, AI systems will be used to hack us. And two, AI systems will themselves become hackers: finding vulnerabilities in all sorts of social, economic, and political systems, and then exploiting them at an unprecedented speed, scale, and scope. It’s not just a difference in degree; it’s a differ- ence in kind. We risk a future of AI systems hacking other AI systems, with humans being little more than collateral damage. This isn’t hyperbole. Okay, maybe it’s a bit of hyperbole, but none of this requires far-future science-fiction technology. I’m not postulating any “singularity,” where the AI-learning feedback loop becomes so fast that it outstrips human understanding. I’m not assuming intelli- gent androids like Data (Star Trek), R2-D2 (Star Wars), or Marvin the Paranoid Android (The Hitchhiker’s Guide to the Galaxy). My sce- narios don’t require evil intent on the part of anyone. We don’t need malicious AI systems like Skynet (Terminator) or the Agents (Matrix). Some of the hacks I will discuss don’t even require majo