http://research.google.com/pubs/atom.xml 2009-11-12T17:20:24-08:00 2009-11-12T11:30:19-08:00 urn:googlelabs:35580

Phishing websites, fraudulent sites that trick viewers into interacting with them, continue to cost Internet users over a billion dollars each year. In this paper, we describe the design and performance characteristics of a scalable machine learning classifier we developed to detect phishing web sites. We use this classifier to maintain Google's phishing blacklist automatically. Our classifier analyzes millions of pages a day, examining the URL and the contents of a page to determine whether or not a page is phishing. Unlike previous work in this field, we train the classifier on a noisy dataset consisting of millions of samples from previously collected live classification data. Despite the noise in the training data, our classifier learns a robust model for identifying phishing pages which correctly classifies more than 90\% of phishing pages several weeks after training concludes.

Colin Whittaker, Brian Ryner, Marria Nazif 2009-11-11T10:17:44-08:00 urn:googlelabs:35648

Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models, Gideon Mann, Ryan McDonald, Mehryar Mohri, Nathan Silberman, Daniel Walker IV

Gideon Mann, Ryan McDonald, Mehryar Mohri, Nathan Silberman, Daniel Walker IV 2009-11-07T23:55:04-08:00 urn:googlelabs:35638

This paper discusses a new method for automatic discovery and organization of descriptive concepts (labels) within large real-world corpora of user-uploaded multimedia, such as YouTube.com. Conversely, it also provides validation of existing labels, if any. While training, our method does not assume any explicit manual annotation other than the weak labels already available in the form of video title, descrip- tion, and tags. Prior work related to such auto-annotation assumed that a vocabulary of labels of interest (e.g., indoor, outdoor, city, landscape) is specified a priori. In contrast, the proposed method begins with an empty vocabulary. It analyzes audiovisual features of 25 million YouTube.com videos – nearly 150 years of video data – effectively searching for consistent correlation between these features and text metadata. It autonomously extends the label vocabulary as and when it discovers concepts it can reliably identify, eventually leading to a vocabulary with thousands of labels and growing. We believe that this work significantly extends the state of the art in multimedia data mining, discovery, and organization based on the technical merit of the proposed ideas as well as the enormous scale of the mining exercise in a very challenging, unconstrained, noisy domain.

Hrishikesh Aradhye, George Toderici, Jay Yagnik 2009-11-03T09:08:53-08:00 urn:googlelabs:35264

A fast and robust method for video contrast enhancement is presented. The method uses the histogram of each frame, along with upper and lower bounds computed per shot in order to enhance the current frame. This ensures that the artifacts introduced during the enhancement is reduced to a minimum. Traditional methods that do not compute per-shot estimates tend to over-enhance parts of the video such as fades and transitions. Our method does not suffer from this problem, which is essential for a fully automatic algorithm. We present the parameters for our methods which yielded the best human feedback, which showed that out of 208 videos, 203 were enhanced, while the remaining 5 were of too poor quality to be enhanced. Additionally, we present a visual comparison of our work with the recently-proposed Weighted Thresholded Histogram Equalization (WTHE) algorithm.

George Toderici, Jay Yagnik 2009-10-28T12:08:37-08:00 urn:googlelabs:35311

Learning a measure of similarity between pairs of objects is a fundamental problem in machine learning. It stands in the core of classifications methods like kernel machines, and is particularly useful for applications like searching for images that are similar to a given image or finding videos that are relevant to a given video. In these tasks, users look for objects that are not only visually similar but also semantically related to a given object. Unfortunately, current approaches for learning similarity do not scale to large datasets, especially when imposing metric constraints on the learned similarity. We describe OASIS, a method for learning pairwise similarity that is fast and scales linearly with the number of objects and the number of non-zero features. Scalability is achieved through online learning of a bilinear model over sparse representations using a large margin criterion and an efficient hinge loss cost. OASIS is accurate at a wide range of scales: on a standard benchmark with thousands of images, it is more precise than state-of-the-art methods, and faster by orders of magnitude. On 2 millions images collected from the web, OASIS can be trained within 3 days on a single CPU. The non-metric similarities learned by OASIS can be transformed into metric similarities, achieving higher precisions than similarities that are learned as metrics in the first place. This suggests an approach for learning a metric from data that is larger by two orders of magnitude than was handled before.

Gal Chechik, Varun Sharma, Uri Shalit, Samy Bengio 2009-10-28T12:08:25-08:00 urn:googlelabs:35313

Group Sparse Coding, Samy Bengio, Fernando Pereira, Yoram Singer, Dennis Strelow

Samy Bengio, Fernando Pereira, Yoram Singer, Dennis Strelow 2009-10-24T16:29:37-08:00 urn:googlelabs:35632

Competitive buffer management with packet dependencies, Alex Kesselman, Boaz Patt-Shamir, Gabriel Scalosub

Alex Kesselman, Boaz Patt-Shamir, Gabriel Scalosub 2009-10-23T18:07:03-08:00 urn:googlelabs:35627

Creating a High-Quality Machine Translation System for a Low-Resource Language: Yiddish, Dmitriy Genzel, Klaus Macherey, Jakob Uszkoreit

Dmitriy Genzel, Klaus Macherey, Jakob Uszkoreit 2009-10-20T23:05:44-08:00 urn:googlelabs:35625

Web-scale extraction of structured data., Michael Cafarella, Jayant Madhavan, Alon Halevy

Michael Cafarella, Jayant Madhavan, Alon Halevy 2009-10-20T23:02:49-08:00 urn:googlelabs:35624

Exploring Schema Repositories with Schemr, Kuang Chen, Jayant Madhavan, Alon Halevy

Kuang Chen, Jayant Madhavan, Alon Halevy