借助人工智能技术的诈骗方式为什么不容易被人们所察觉，它一般法采用哪些人工智能技术

选自Medium作者：James Le机器之心编译参与：白悦、黄小天我们为什么需要「机器学习」？机器学习对于那些我们直接编程太过复杂的任务来说是必需的。有些任务很复杂，以至于人类不可能解决任务中所有的细节并精确地编程。所以，我们向机器学习算法提供大量的数据，让算法通过探索数据并找到一个可以实现程序员目的的模型来解决这个问题。我们来看两个例子：写一个程序去识别复杂场景中照明条件下新视角的三维物体是很困难的。我们不知道编写什么程序，因为我们并不了解它在我们大脑中运作的机制，即便知道如何实现，写出来的程序也可能会非常复杂。写一个程序去计算信用卡诈骗的概率是很困难的。因为可能没有任何既简单又可靠的规则，我们需要结合大量的弱规则去判别。欺骗是可以转移目标的，程序需要不断更改。接着出现了机器学习方法：我们不需为每个特定的任务手动编程，只要收集大量的样本，为给定的输入指定正确的输出。机器学习算法利用这些样本去生成完成指定工作的程序。学习算法产生的程序可能与典型的手写程序非常不同，它可能包含数百万个数字。如果我们做得正确，这个程序将像处理训练集上的样本一样来处理新样本。如果数据改变，程序也可以通过训练新数据改变。你应该注意到，目前大量的计算比支付给程序员编写一个特定任务的程序便宜。鉴于此，机器学习最适用任务的例子包括：模式识别：真实场景中的物体，面部识别或面部表情，口语。异常识别：不寻常的信用卡交易序列，核电站传感器读数的异常模式。预测：未来股票价格或货币汇率，一个人喜欢什么电影。什么是神经网络？

Require that developers of the most powerful AI systems share their safety test results and other critical information with the U.S.government.In accordance with the Defense Production Act,the Order will require that companies developing any foundation model that poses a serious risk to national security,national economic security,or national public health and safety must notify the federal government when training the model,and must share the results of all red-team safety tests.These measures will ensure AI systems are safe,secure,and trustworthy before companies make them public.Develop standards,tools,and tests to help ensure that AI systems are safe,secure,and trustworthy.The National Institute of Standards and Technology will set the rigorous standards for extensive red-team testing to ensure safety before public release.The Department of Homeland Security will apply those standards to critical infrastructure sectors and establish the AI Safety and Security Board.The Departments of Energy and Homeland Security will also address AI systems’ threats to critical infrastructure,as well as chemical,biological,radiological,nuclear,and cybersecurity risks.Together,these are the most significant actions ever taken by any government to advance the field of AI safety.Protect against the risks of using AI to engineer dangerous biological materials by developing strong new standards for biological synthesis screening.Agencies that fund life-science projects will establish these standards as a condition of federal funding,creating powerful incentives to ensure appropriate screening and manage risks potentially made worse by AI.Protect Americans from AI-enabled fraud and deception by establishing standards and best practices for detecting AI-generated content and authenticating official content.The Department of Commerce will develop guidance for content authentication and watermarking to clearly label AI-generated content.Federal agencies will use these tools to make it easy for Americans to know that the communications they receive from their government are authentic—and set an example for the private sector and governments around the world.

transformative developments yet tocome.27LLMs provide substantial opportunities to transformthe economy and society.For example,LLMs can automate the process of writing code andTransport apps like Google Maps,and CityMapper,use AI.Artificial Intelligence in Banking Industry:A Review on Fraud Detection,Credit Management,and Document Processing,ResearchBerg Review of Science and Technology,2018.Accelerating fusion science through learned plasma control,Deepmind,2022; Magnetic control of tokamak plasmasthrough deep reinforcement learning,Degrave et al.,2022.Why Artificial Intelligence Could Speed Drug Discovery,Morgan Stanley,2022.AI Is Essential for Solving the Climate Crisis,BCG,2022.General Purpose Technologies – Handbook of Economic Growth,National Bureau of Economic Research,2005.The UK Science and Technology Framework,Department for Science,Innovation and Technology,2023.In 2022 annual revenues generated by UK AI companies totalled an estimated £10.6 billion.AI Sector Study 2022,DSIT,2023.DSIT analysis estimates over 50,000 full time workers are employed in AI roles in AI companies.AI Sector Study 2022,DSIT,2023.For example,AI can potentially improve health and safety in mining while also improving efficiency.See AI on-side:howartificial intelligence is being used to improve health and safety in mining,Axora,2023.Box 1.1 gives further examples of AIdriving efficiency improvements.Large Language Models Will Define Artificial Intelligence,Forbes,2023; Scaling Language Models:Methods,Analysis &Insights from Training Gopher,Borgeaud et al.,2022.A pro-innovation approach to AI regulationfixing programming bugs.The technology can support genetic medicine by identifying linksbetween genetic sequences and medical conditions.It can support people to review and