Adobe says it can identify manipulated images using AI
Adobe的人工智能可以让PS的印记无处遁形
Adobe's tool looks for clues such as noise inconsistencies
Adobe的工具发现诸如噪声不一致的线索。
The company behind the photo-editing program Photoshop says it has developed a tool that can detect if an image has been tampered with.
这家研发了相片编辑软件Photoshop的公司说他们已经开发了一个能够识别到一个图像是否被篡改过的工具
Adobe's algorithm can detect unusual RGB (red, green, blue) values and noise streamsAdobe算法可以检测出异常的RGB（红、绿、蓝）值和噪点流。
Vlad Morarium, an Adobe researcher, employed artificial intelligence to scan for signs of manipulation that are not usually visible to the naked eye.
Vlad Morarium是一名Adobe研究员，他利用人工智能扫描人们通常肉眼看不到的伪造痕迹。
The AI could tell if an element had been added, moved or cut from a photo.
人工智能可以告诉你是否在原有照片上有增加和移走或剪切掉的元素。
But the company warned that no piece of technology could provide a foolproof verification system.
但是公司警告说并没有一种技术能够提供很完美的验证系统。
Photoshop, which was created 28 years ago, is a powerful image editor, and its name has become a verb for image manipulation.
28年前创造出来的photoshop是一种功能强大的图形处理软件，它的名字已经成为了一个制作图像的动词。
Existing verification tools can scan an image file's metadata - which contains information on when and where a photo was taken - for signs of mischief, and look for things like inconsistent lighting.
现有的验证工具能够扫描一个图形文件的元数据-它包含了图片在何时何地拍摄的-以找出伪造的痕迹，并寻找其它例如像光线不一致的迹象。
But such tests are easily defeated.
但这些检测很容易被打败。
Mr Morarium, who spent 14 years researching ways to spot image manipulation, taught an artificial intelligence network to recognise signs of colour change and noise inconsistencies in tens of thousands of pictures.
Morarium先生花了14年研究检测图形伪造，他教给了一个人工智能网如何分辨出图形的色彩变化和图形噪音的不一致。
One expert said the core techniques in Adobe and Darpa's research have been widely known for nearly 20 years, but the use of machine learning might help reveal tampering that is not immediately apparent.
一位专家说，近20年来Adobe和DARPA研究的核心技术已经被广泛了解，但是使用机器学习也许能有助与使那些不是显而易见的篡改暴露原形。
👇

欢迎大家扫码关注
每天学点英语，其实很有必要
继续阅读
阅读原文