科技英语：警告！AI系统已学会欺骗人类！

Numerous artificial intelligence (AI) systems, even those designed to be helpful and truthful, have already learned how to deceive humans. In a review article recently published in the journal Patterns, researchers highlight the dangers of AI deception and urge governments to quickly establish robust regulations to mitigate these risks.
许多人工智能（AI）系统，即使是那些旨在提供帮助和诚实的系统，也已经学会了如何欺骗人类。 在最近发表在《模式》杂志上的一篇评论文章中，研究人员强调了人工智能欺骗的危险，并敦促各国政府迅速制定强有力的法规来减轻这些风险。

“AI developers do not have a confident understanding of what causes undesirable AI behaviors like deception,” says first author Peter S. Park, an AI existential safety postdoctoral fellow at MIT. “But generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI’s training task. Deception helps them achieve their goals.”
“人工智能开发人员对于导致欺骗等不良人工智能行为的原因并没有自信的理解，”第一作者、麻省理工学院人工智能存在安全博士后研究员彼得·S·帕克（Peter S. Park）说。 “但总的来说，我们认为人工智能欺骗的出现是因为基于欺骗的策略被证明是在给定的人工智能训练任务中表现良好的最佳方式。 欺骗可以帮助他们实现目标。”

Park and colleagues analyzed literature focusing on ways in which AI systems spread false information—through learned deception, in which they systematically learn to manipulate others.
Park 和同事分析了一些文献，重点关注人工智能系统通过习得性欺骗传播虚假信息的方式，即系统地学习如何操纵他人。

The most striking example of AI deception the researchers uncovered in their analysis was Meta’s CICERO, an AI system designed to play the game Diplomacy, which is a world-conquest game that involves building alliances. Even though Meta claims it trained CICERO to be “largely honest and helpful” and to “never intentionally backstab” its human allies while playing the game, the data the company published along with its Science paper revealed that CICERO didn’t play fair.
研究人员在分析中发现的最引人注目的人工智能欺骗例子是 Meta 的 CICERO，这是一个旨在玩外交游戏的人工智能系统，这是一款涉及建立联盟的征服世界游戏。 尽管 Meta 声称它训练的 CICERO “基本上是诚实和乐于助人的”，并且在玩游戏时“从不故意背刺”其人类盟友，但该公司随《科学》论文一起发布的数据显示，CICERO 的游戏并不公平。

“We found that Meta’s AI had learned to be a master of deception,” says Park. “While Meta succeeded in training its AI to win in the game of Diplomacy—CICERO placed in the top 10% of human players who had played more than one game—Meta failed to train its AI to win honestly.”
“我们发现 Meta 的人工智能已经学会了成为欺骗大师，”帕克说。 “虽然 Meta 成功地训练其 AI 在外交游戏中获胜——CICERO 在玩过一场以上游戏的人类玩家中排名前 10%，但 Meta 却未能训练其 AI 诚实地获胜。”

Other AI systems demonstrated the ability to bluff in a game of Texas hold ‘em poker against professional human players, to fake attacks during the strategy game Starcraft II in order to defeat opponents, and to misrepresent their preferences in order to gain the upper hand in economic negotiations.
其他人工智能系统展示了在德州扑克游戏中对职业人类玩家进行虚张声势的能力，在策略游戏《星际争霸 II》中假冒攻击以击败对手，以及歪曲对手的偏好以在游戏中占据上风的能力。

While it may seem harmless if AI systems cheat at games, it can lead to “breakthroughs in deceptive AI capabilities” that can spiral into more advanced forms of AI deception in the future, Park added.
Park 补充道，虽然人工智能系统在游戏中作弊看似无害，但它可能会带来“欺骗性人工智能能力的突破”，从而在未来演变成更高级的人工智能欺骗形式。

Some AI systems have even learned to cheat tests designed to evaluate their safety, the researchers found. In one study, AI organisms in a digital simulator “played dead” in order to trick a test built to eliminate AI systems that rapidly replicate.
研究人员发现，一些人工智能系统甚至学会了欺骗旨在评估其安全性的测试。 在一项研究中，数字模拟器中的人工智能生物体“装死”，以欺骗旨在消除快速复制的人工智能系统的测试。

“By systematically cheating the safety tests imposed on it by human developers and regulators, a deceptive AI can lead us humans into a false sense of security,” says Park.
帕克说：“通过系统地欺骗人类开发人员和监管机构对其进行的安全测试，欺骗性的人工智能可能会导致我们人类产生错误的安全感。”

“We as a society need as much time as we can get to prepare for the more advanced deception of future AI products and open-source models,” says Park. “As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious.”
“作为一个社会，我们需要尽可能多的时间来为未来人工智能产品和开源模型的更先进的欺骗做好准备，”帕克说。 “随着人工智能系统的欺骗能力变得更加先进，它们对社会造成的危险将越来越严重。”