Luis von Ahn

Designing games with a purpose

Data generated as a side effect of game play also solves computational problems and trains AI algorithms.

reCAPTCHA: Human-Based Character Recognition via Web Security Measures

CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) are widespread security measures on the World Wide Web that prevent automated programs from abusing online services. They do so by asking humans to perform a task that computers cannot yet perform, such as deciphering distorted characters. Our research explored whether such human effort can be channeled into a useful purpose: helping to digitize old printed material by asking users to decipher scanned words from books that computerized optical character recognition failed to recognize. We showed that this method can transcribe text with a word accuracy exceeding 99%, matching the guarantee of professional human transcribers. Our apparatus is deployed in more than 40,000 Web sites and has transcribed over 440 million words.

Telling humans and computers apart automatically

How lazy cryptographers do AI.

Peekaboom: a game for locating objects in images

We introduce Peekaboom, an entertaining web-based game that can help computers locate objects in images. People play the game because of its entertainment value, and as a side effect of them playing, we collect valuable image metadata, such as which pixels belong to which object in the image. The collected data could be applied towards constructing more accurate computer vision algorithms, which require massive amounts of training and testing data not currently available. Peekaboom has been played by thousands of people, some of whom have spent over 12 hours a day playing, and thus far has generated millions of data points. In addition to its purely utilitarian aspect, Peekaboom is an example of a new, emerging class of games, which not only bring people together for leisure purposes, but also exist to improve artificial intelligence. Such games appeal to a general audience, while providing answers to problems that computers cannot yet solve.

Improving accessibility of the web with a computer game

Images on the Web present a major accessibility issue for the visually impaired, mainly because the majority of them do not have proper captions. This paper addresses the problem of attaching proper explanatory text descriptions to arbitrary images on the Web. To this end, we introduce Phetch, an enjoyable computer game that collects explanatory descriptions of images. People play the game because it is fun, and as a side effect of game play we collect valuable information. Given any image from the World Wide Web, Phetch can output a correct annotation for it. The collected data can be applied towards significantly improving Web accessibility. In addition to improving accessibility, Phetch is an example of a new class of games that provide entertainment in exchange for human processing power. In essence, we solve a typical computer vision problem with HCI tools alone.

Matchin: eliciting user preferences with an online game

Eliciting user preferences for large datasets and creating rankings based on these preferences has many practical applications in community-based sites. This paper gives a new method to elicit user preferences that does not ask users to tell what they prefer, but rather what a random person would prefer, and rewards them if their prediction is correct. We provide an implementation of our method as a two-player game in which each player is shown two images and asked to click on the image their partner would prefer. The game has proven to be enjoyable, has attracted tens of thousands of people and has already collected millions of judgments. We compare several algorithms for combining these relative judgments between pairs of images into a total ordering of all images and present a new algorithm to perform collaborative filtering on pair-wise relative judgments. In addition, we show how merely observing user preferences on a specially chosen set of images can predict a users gender with high probability.

k-anonymous message transmission

Informally, a communication protocol is sender k - anonymous if it can guarantee that an adversary, trying to determine the sender of a particular message, can only narrow down its search to a set of k suspects. Receiver k-anonymity places a similar guarantee on the receiver: an adversary, at best, can only narrow down the possible receivers to a set of size k. In this paper we introduce the notions of sender and receiver k-anonymity and consider their applications. We show that there exist simple and efficient protocols which are k-anonymous for both the sender and the receiver in a model where a polynomial time adversary can see all traffic in the network and can control up to a constant fraction of the participants. Our protocol is provably secure, practical, and does not require the existence of trusted third parties. This paper also provides a conceptually simple augmentation to Chaums DC-Nets that adds robustness against adversaries who attempt to disrupt the protocol through perpetual transmission or selective non-participation.

Why do tagging systems work

The panel will explore the relevance of the emerging tagging systems (Flickr, Del.icio.us, RawSugar and more). Why do they seem to work? What kinds of incentives are required for users to participate? Will tagging survive and scale to mass adoption? What are the behavioral, economic, and social models that underlie each tagging system? What are the dynamics of those systems, and how are they derived from the specific applications design and affordances?.We will demand answers to these questions and others from some of the pioneering practitioners and academics in the field. Bring your wireless laptop to participate in a live tagging experiment! The experiment results will be shown and discussed at the end of the panel. To add to the fun, parts of the discussion will be motivated by short video segments.

Selectively traceable anonymity

Anonymous communication can, by its very nature, facilitate socially unacceptable behavior; such abuse of anonymity is a serious impediment to its widespread deployment. This paper studies two notions related to the prevention of abuse. The first is selective traceability, the property that a messages sender can be traced with the help of an explicitly stated set of parties. The second is noncoercibility, the property that no party can convince an adversary (using technical means) that he was not the sender of a message. We show that, in principal, almost any anonymity scheme can be made selectively traceable, and that a particular anonymity scheme can be modified to be noncoercible.

Search war: a game for improving web search

We present a competitive online game called Search War, which collects data that is useful for improving Web search. Specifically, as a by product of gameplay, players will provide, for a given web page, an evaluation of its relevance to a particular search query as well as its most salient purpose.