Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる

インシデント 13: High-Toxicity Assessed on Text Involving Women and Minority Groups

概要: Google's Perspective API, which assigns a toxicity score to online text, seems to award higher toxicity scores to content involving non-white, male, Christian, heterosexual phrases.

ツール

新しいレポート新しいレポート新しいレスポンス新しいレスポンス発見する発見する履歴を表示履歴を表示

組織

すべての組織を表示
推定: Googleが開発し提供したAIシステムで、Women と Minority Groupsに影響を与えた

インシデントのステータス

インシデントID
13
レポート数
9
インシデント発生日
2017-02-27
エディタ
Sean McGregor
Applied Taxonomies
CSETv0, GMF, CSETv1, MIT

CSETv1 分類法のクラス

分類法の詳細

Incident Number

The number of the incident in the AI Incident Database.
 

13

CSETv0 分類法のクラス

分類法の詳細

Problem Nature

Indicates which, if any, of the following types of AI failure describe the incident: "Specification," i.e. the system's behavior did not align with the true intentions of its designer, operator, etc; "Robustness," i.e. the system operated unsafely because of features or changes in its environment, or in the inputs the system received; "Assurance," i.e. the system could not be adequately monitored or controlled during operation.
 

Specification, Robustness

Physical System

Where relevant, indicates whether the AI system(s) was embedded into or tightly associated with specific types of hardware.
 

Software only

Level of Autonomy

The degree to which the AI system(s) functions independently from human intervention. "High" means there is no human involved in the system action execution; "Medium" means the system generates a decision and a human oversees the resulting action; "low" means the system generates decision-support output and a human makes a decision and executes an action.
 

High

Nature of End User

"Expert" if users with special training or technical expertise were the ones meant to benefit from the AI system(s)’ operation; "Amateur" if the AI systems were primarily meant to benefit the general public or untrained users.
 

Amateur

Public Sector Deployment

"Yes" if the AI system(s) involved in the accident were being used by the public sector or for the administration of public goods (for example, public transportation). "No" if the system(s) were being used in the private sector or for commercial purposes (for example, a ride-sharing company), on the other.
 

No

Data Inputs

A brief description of the data that the AI system(s) used or were trained on.
 

Online comments

GMF 分類法のクラス

分類法の詳細

Known AI Goal Snippets

One or more snippets that justify the classification.
 

(Snippet Text: However, computer scientists and others on the internet have found the system unable to identify a wide swath of hateful comments, while categorizing innocuous word combinations like “hate is bad” and “garbage truck” as overwhelmingly toxic., Related Classifications: Hate Speech Detection)

MIT 分類法のクラス

Machine-Classified
分類法の詳細

Risk Subdomain

A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
 

1.1. Unfair discrimination and misrepresentation

Risk Domain

The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
 
  1. Discrimination and Toxicity

Entity

Which, if any, entity is presented as the main cause of the risk
 

AI

Timing

The stage in the AI lifecycle at which the risk is presented as occurring
 

Post-deployment

Intent

Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
 

Unintentional

インシデントレポート

レポートタイムライン

+2
Alphabet’s hate-fighting AI doesn’t understand hate yet
Google Robo-Tool Flags Conservative Comments as “Toxic”+3
Google's New Hate Speech Algorithm Has a Problem With Jews
+1
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
Alphabet’s hate-fighting AI doesn’t understand hate yet

Alphabet’s hate-fighting AI doesn’t understand hate yet

qz.com

Security researchers show Google's anti-internet troll AI platform is easily deceived

Security researchers show Google's anti-internet troll AI platform is easily deceived

techxplore.com

Google Robo-Tool Flags Conservative Comments as “Toxic”

Google Robo-Tool Flags Conservative Comments as “Toxic”

infowars.com

Google's New Hate Speech Algorithm Has a Problem With Jews

Google's New Hate Speech Algorithm Has a Problem With Jews

tabletmag.com

You weren’t supposed to actually implement it, Google

You weren’t supposed to actually implement it, Google

blog.conceptnet.io

Google's Anti-Bullying AI Mistakes Civility for Decency

Google's Anti-Bullying AI Mistakes Civility for Decency

motherboard.vice.com

Google’s comment-ranking system will be a hit with the alt-right

Google’s comment-ranking system will be a hit with the alt-right

engadget.com

From Toxicity in Online Comments to Incivility in American News: Proceed with Caution

From Toxicity in Online Comments to Incivility in American News: Proceed with Caution

arxiv.org

AI displays bias and inflexibility in civility detection, study finds

AI displays bias and inflexibility in civility detection, study finds

venturebeat.com

Alphabet’s hate-fighting AI doesn’t understand hate yet
qz.com · 2017

Yesterday, Google and its sister Alphabet company Jigsaw announced Perspective, a tool that uses machine learning to police the internet against hate speech. The company heralded the tech as a nascent but powerful weapon in combatting onlin…

Security researchers show Google's anti-internet troll AI platform is easily deceived
techxplore.com · 2017

In the examples below on hot-button topics of climate change, Brexit and the recent US election -- which were taken directly from the Perspective API website -- the UW team simply misspelled or added extraneous punctuation or spaces to the …

Google Robo-Tool Flags Conservative Comments as “Toxic”
infowars.com · 2017

The Google AI tool used to flag “offensive comments” has a seemingly built-in bias against conservative and libertarian viewpoints.

Perspective API, a “machine learning model” developed by Google which scores “the perceived impact a comment…

Google's New Hate Speech Algorithm Has a Problem With Jews
tabletmag.com · 2017

Don’t you just hate how vile some people are on the Internet? How easy it’s become to say horrible and hurtful things about other groups and individuals? How this tool that was supposed to spread knowledge, amity, and good cheer is being us…

You weren’t supposed to actually implement it, Google
blog.conceptnet.io · 2017

Last month, I wrote a blog post warning about how, if you follow popular trends in NLP, you can easily accidentally make a classifier that is pretty racist. To demonstrate this, I included the very simple code, as a “cautionary tutorial”.

T…

Google's Anti-Bullying AI Mistakes Civility for Decency
motherboard.vice.com · 2017

As politics in the US and Europe have become increasingly divisive, there's been a push by op-ed writers and politicians alike for more "civility" in our debates, including online. Amidst this push comes a new tool by Google's Jigsaw that u…

Google’s comment-ranking system will be a hit with the alt-right
engadget.com · 2017

A recent, sprawling Wired feature outlined the results of its analysis on toxicity in online commenters across the United States. Unsurprisingly, it was like catnip for everyone who's ever heard the phrase "don't read the comments." Accordi…

From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
arxiv.org · 2021

Abstract

The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists. Computational tools for detecting online incivility for English are now fairly accessible and potentiall…

AI displays bias and inflexibility in civility detection, study finds
venturebeat.com · 2021

According to a 2019 Pew Center survey, the majority of respondents believe the tone and nature of political debate in the U.S. have become more negative and less respectful. This observation has motivated scientists to study the civility or…

バリアント

「バリアント」は既存のAIインシデントと同じ原因要素を共有し、同様な被害を引き起こし、同じ知的システムを含んだインシデントです。バリアントは完全に独立したインシデントとしてインデックスするのではなく、データベースに最初に投稿された同様なインシデントの元にインシデントのバリエーションとして一覧します。インシデントデータベースの他の投稿タイプとは違い、バリアントではインシデントデータベース以外の根拠のレポートは要求されません。詳細についてはこの研究論文を参照してください

よく似たインシデント

テキスト類似度による

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 レポート
Gender Biases in Google Translate

Semantics derived automatically from language corpora contain human-like biases

Apr 2017 · 10 レポート
TayBot

Danger, danger! 10 alarming examples of AI gone wild

Mar 2016 · 28 レポート
前のインシデント次のインシデント

よく似たインシデント

テキスト類似度による

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 レポート
Gender Biases in Google Translate

Semantics derived automatically from language corpora contain human-like biases

Apr 2017 · 10 レポート
TayBot

Danger, danger! 10 alarming examples of AI gone wild

Mar 2016 · 28 レポート

リサーチ

  • “AIインシデント”の定義
  • “AIインシデントレスポンス”の定義
  • データベースのロードマップ
  • 関連研究
  • 全データベースのダウンロード

プロジェクトとコミュニティ

  • AIIDについて
  • コンタクトとフォロー
  • アプリと要約
  • エディタのためのガイド

インシデント

  • 全インシデントの一覧
  • フラグの立ったインシデント
  • 登録待ち一覧
  • クラスごとの表示
  • 分類法

2023 - AI Incident Database

  • 利用規約
  • プライバシーポリシー
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • f28fa7c