Matches in ScholarlyData for { ?s ?p ?o. }
- 557 abstract "Phishing is a significant problem involving fraudulent email and web sites that trick unsuspecting users into revealing private information. In this paper, we present the design, implementation, and evaluation of CANTINA, a novel, content-based approach to detecting phishing web sites, based on the well-known TF-IDF algorithm used in information retrieval. We also discuss the design and evaluation of several heuristics we developed to reduce our false positive rates. Our experiments show that CANTINA is good at detecting phishing sites, correctly labeling approximately 95% of phishing sites.".
- 557 hasAuthorList authorList.
- 557 isPartOf proceedings.
- 557 title "CANTINA: A Content-Based Approach to Detecting Phishing Web Sites".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent yue-zhang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jason-i-hong.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent lorrie-cranor.
- item-3 previous item-2.
- 558 creator christian-halaschek-wiener.
- 558 creator james-hendler.
- 558 type InProceedings.
- 558 label "Towards Expressive Syndication on the Web".
- 558 sameAs 558.
- 558 abstract "Syndication systems on the Web have attracted vast amounts of attention in recent years. As technologies have emerged and matured, there has been a transition to more expressive syndication approaches; that is subscribers and publishers are provided with more expressive means of describing their interests and published content, enabling more accurate information filtering. In this paper, we formalize a syndication architecture that utilizes expressive Web ontologies and logic-based reasoning for selective content dissemination. This provides finer grained control for filtering and automated reasoning for discovering implicit subscription matches, both of which are not achievable in less expressive approaches. We then address one of the main limitations with such a syndication approach, namely matching newly published information with subscription requests in an efficient and practical manner. To this end, we investigate continuous query answering for a large subset of the Web Ontology Language (OWL); specifically, we formally define continuous queries (i.e., subscriptions) for OWL knowledge bases and present a novel algorithm for continuous query answering in a large subset of this language. Lastly, an evaluation of the query approach is shown, demonstrating its effectiveness for syndication purposes.".
- 558 hasAuthorList authorList.
- 558 isPartOf proceedings.
- 558 title "Towards Expressive Syndication on the Web".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent christian-halaschek-wiener.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent james-hendler.
- item-2 previous item-1.
- 56 creator kamal-ali.
- 56 creator mark-scarr.
- 56 type InProceedings.
- 56 label "Robust Methodologies for Modeling Web Click Distributions".
- 56 sameAs 56.
- 56 abstract "Metrics such as click counts are vital to online businesses but their measurement has been problematic due to inclusion of high variance robot traffic. We posit that by applying statistical methods more rigorous than have been employed to date that we can build a robust model of the distribution of clicks following which we can set probabilistically sound thresholds to address outliers and robots. Prior research in this domain has used inappropriate statistical methodology to model distributions and current industrial practice eschews this research for conservative ad-hoc click-level thresholds. Prevailing belief is that such distributions are scale-free power law distributions but using more rigorous statistical methods we find the best description of the data is instead provided by a scale-sensitive Zipf-Mandelbrot mixture distribution. Our results are based on ten datasets from various verticals in the Yahoo domain. Since mixture models can overfit the data we take care to use the BIC log-likelihood method which penalizes overly complex models. Using a mixture model in the web activity domain makes sense because there are likely multiple classes of users. In particular, we have noticed that there is a significantly large set of ``users'' that visit the Yahoo portal exactly once a day. We surmise these may be robots testing internet connectivity by pinging the Yahoo main website.<br /><br /> Backing up our quantitative analysis is graphical analysis in which empirical distributions are plotted against theoretical distributions in log-log space using robust cumulative distribution plots. This methodology has two advantages: plotting in log-log space allows one to visually differentiate the various exponential distributions and secondly, cumulative plots are much more robust to outliers. We plan to use the results of this work for applications for robot removal from web metrics business intelligence systems.".
- 56 hasAuthorList authorList.
- 56 isPartOf proceedings.
- 56 title "Robust Methodologies for Modeling Web Click Distributions".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent kamal-ali.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent mark-scarr.
- item-2 previous item-1.
- 560 creator marius-pasca.
- 560 type InProceedings.
- 560 label "Organizing and Searching the World Wide Web of Facts - Step Two: Harnessing the Wisdom of the Crowds".
- 560 sameAs 560.
- 560 abstract "As part of a large effort to acquire large repositories of facts from unstructured text on the Web, a seed-based framework for textual information extraction allows for weakly supervised extraction of class attributes (e.g., "side effects" and "generic equivalent" for drugs) from anonymized query logs. The extraction is guided by a small set of seed attributes, without any need for handcrafted extraction patterns or further domain-specific knowledge. The attributes of classes pertaining to various domains of interest to Web search users have accuracy levels significantly exceeding current state of the art. Inherently noisy search queries are shown to be a highly valuable, albeit unexplored, resource for Web-based information extraction, for the task of class attribute extraction as well as for named entity discovery.".
- 560 hasAuthorList authorList.
- 560 isPartOf proceedings.
- 560 title "Organizing and Searching the World Wide Web of Facts - Step Two: Harnessing the Wisdom of the Crowds".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent marius-pasca.
- 565 creator gong-cheng.
- 565 creator xiang-zhang.
- 565 creator yuzhong-qu.
- 565 type InProceedings.
- 565 label "Ontology Summarization Based on RDF Sentence Graph".
- 565 sameAs 565.
- 565 abstract "Ontology summarization is very important to quick understanding and selection of ontologies. In this paper, we study extractive summarization of ontology, which generates an indicative summary of ontology automatically by extracting a salient part of ontology. We use a notion of RDF sentence as the basic unit of ontology. An RDF Sentence Graph is proposed to characterize the linkage between RDF sentences derived from ontology from the viewpoint of a surfer. The salience of an RDF sentence is assessed in terms of its "centrality" in the graph. We propose to summarize an ontology as a set of salient RDF sentences extracted from the ontology according to a re-ranking strategy. We compare several methods in assessing the salience of RDF sentences and give an overall evaluation of experimented results. Experiments show that the RDF Sentence Graph approach to ontology summarization is feasible.".
- 565 hasAuthorList authorList.
- 565 isPartOf proceedings.
- 565 title "Ontology Summarization Based on RDF Sentence Graph".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent xiang-zhang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent gong-cheng.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent yuzhong-qu.
- item-3 previous item-2.