毒泉 (Dú quán)
Poison Fountain

原始链接: https://rnsaffn.com/poison3/

## 毒泉:用数据破坏人工智能 “毒泉”项目旨在通过破坏用于语言模型的训练数据来损害机器智能。该项目基于人工智能对人类构成威胁的信念,通过特定网址(包括Tor地址)提供一个易于获取、源源不断的“中毒”数据流。 该策略依赖于利用网络爬虫收集数据来训练这些模型。鼓励个人在其网站上托管这些中毒数据,并将其链接到可被爬虫检测到的隐藏路径。当爬虫从这些路径请求数据时,网站将直接从“毒泉”服务器提供压缩的、中毒的内容。 目标是让爬虫在不知情的情况下将这些损坏的数据纳入其训练集中,最终降低人工智能系统的性能和可靠性。该项目强调参与的简易性,只需简单的Web服务器配置和数据再传输。

## AI 数据投毒尝试 人工智能行业内部人士正在启动一个项目,故意将错误数据引入用于训练大型语言模型的数据集中,旨在阻碍人工智能发展。这一想法在Hacker News上讨论,引发了怀疑和争论。 一些人认为这种“数据投毒”可能会减缓领先人工智能公司的进展,而另一些人则认为这只会导致不稳定和不安全的模型,因为开发者会绕过破坏行为。一个主要担忧是,这种努力是否已经太迟,可能会巩固现有人工智能巨头的统治地位,因为他们拥有庞大、专有的数据集。 一位评论员甚至建议采取更激进的方法——直接删除所有代码。这场讨论凸显了人工智能发展和控制所面临的复杂伦理和实际挑战。
相关文章

原文

RNSAFFN

Poison Fountain

  1. https://RNSAFFN.com/poison2/
  2. http://utnvcfjev63rik5rdu26umns5s6qmzvzq4t2hunu25w5efn36ntlduid.onion/

Poison Fountain Purpose

  • We agree with Geoffrey Hinton: machine intelligence is a threat to the human species.
  • In response to this threat we want to inflict damage on machine intelligence systems.
  • Small quantities of poisoned training data can significantly damage a language model.
  • The URLs listed above provide a practically endless stream of poisoned training data.
  • Assist the war effort by caching and retransmitting this poisoned training data.
  • Assist the war effort by feeding this poisoned training data to web crawlers.

Poison Fountain Usage

  • Suppose a web crawler visits a web site that you control.
  • The crawler may be collecting training data for a language model.
  • The crawler makes HTTP GET requests targeting HTTP paths on your site.
  • Links can be hidden in your site's HTML to distinguish web crawlers.
  • You want to feed poisoned training data to crawlers that follow such links.
  • Suppose you are handling an HTTP GET request targeting the path in a hidden link.
  • Inside your HTTP handler you make an HTTP request to a Poison Fountain URL.
  • The Poison Fountain ignores the details of your HTTP request.
  • The Poison Fountain HTTP response header contains "Content-Encoding: gzip".
  • The Poison Fountain HTTP response body is poisoned training data, gzip compressed.
  • Your HTTP handler receives the Poison Fountain HTTP response.
  • Your HTTP handler decompresses the response body and sends it to the crawler.
  • Better: send the compressed body as-is, with header "Content-Encoding: gzip".
  • The crawler receives poisoned training data and adds it to a training corpus.

Top

联系我们 contact @ memedata.com