Account Owners Research Articles

Profiling Online Social Behaviors for Compromised Account Detection

Account compromization is a serious threat to users of online social networks (OSNs). While relentless spammers exploit the established trust relationships between account owners and their friends to efficiently spread malicious spam, timely detection of compromised accounts is quite challenging due to the well established trust relationship between the service providers, account owners, and their friends. In this paper, we study the social behaviors of OSN users, i.e., their usage of OSN services, and the application of which in detecting the compromised accounts. In particular, we propose a set of social behavioral features that can effectively characterize the user social activities on OSNs. We validate the efficacy of these behavioral features by collecting and analyzing real user clickstreams to an OSN website. Based on our measurement study, we devise individual user’s social behavioral profile by combining its respective behavioral feature metrics. A social behavioral profile accurately reflects a user’s OSN activity patterns. While an authentic owner conforms to its account’s social behavioral profile involuntarily, it is hard and costly for impostors to feign. We evaluate the capability of the social behavioral profiles in distinguishing different OSN users, and our experimental results show the social behavioral profiles can accurately differentiate individual OSN users and detect compromised accounts.

Using support vector machine ensembles for target audience classification on Twitter.

The vast amount and diversity of the content shared on social media can pose a challenge for any business wanting to use it to identify potential customers. In this paper, our aim is to investigate the use of both unsupervised and supervised learning methods for target audience classification on Twitter with minimal annotation efforts. Topic domains were automatically discovered from contents shared by followers of an account owner using Twitter Latent Dirichlet Allocation (LDA). A Support Vector Machine (SVM) ensemble was then trained using contents from different account owners of the various topic domains identified by Twitter LDA. Experimental results show that the methods presented are able to successfully identify a target audience with high accuracy. In addition, we show that using a statistical inference approach such as bootstrapping in over-sampling, instead of using random sampling, to construct training datasets can achieve a better classifier in an SVM ensemble. We conclude that such an ensemble system can take advantage of data diversity, which enables real-world applications for differentiating prospective customers from the general audience, leading to business advantage in the crowded social media space.

FATCA for CLOs: Status Report

The Foreign Account Tax Compliance Act (FATCA) requires foreign financial institutions (FFIs) to conduct due diligence on their financial account owners to identify specified U.S. persons, report U.S. account owners to the U.S. IRS, and apply withholding as appropriate. The definition of “financial institution” is very broad and will encompass nearly all non-U.S. collateralized loan obligation (CLO) vehicles. CLOs invest in debt instruments, many of which are issued by U.S. corporations. Should the CLO vehicle fail to become FATCA compliant, issuers of U.S. debt will be required to withhold 30% of certain payments of interest starting on July 1, 2014, and certain payments of gross proceeds from the sale or other disposition of the underlying loans starting in 2017. To become compliant under FATCA and avoid the additional U.S. tax withholding, a CLO vehicle will be required either to enter into an FFI agreement with the IRS or to qualify under one of the categories established for deemed-compliant entities that are considered to present a lower risk of tax evasion. This special category falls into two regimes: registered deemed compliant, whereby the FFI still must register with the IRS but does not need an FFI agreement, and certified deemed compliant, whereby the entity can certify its compliance to counterparties and does not need to enter into an FFI agreement or register with the IRS. In addition, deemed-compliant status can be achieved by complying with the terms of an intergovernmental agreement (IGA). In response to the industry-specific issues raised by CLOs, the International Swaps and Derivatives Association, the Loan Syndications and Trading Association, and the Securities Industry and Financial Markets Association have been active in their efforts to carve out exceptions for both existing and new CLO vehicles. <b>TOPICS:</b>CLOs, CDOs, and other structured credit, legal/regulatory/public policy

Stopping spam with sending session verification

Spam has become one of the most signicant problems for Internet communication and users today. The traditional ltering methods and signature-based spam blocking systems that have come into prominence recently fall short, as statistics demonstrate that spam further mounts up day after day. In this study, a new method is recommended to block spam mails. In this recommended method, a mail sending session is veried during mail envelope communication by adding small attachments to the simple mail transfer protocol, so spam mails can be blocked before leaving the sender domain or relay machine. Additionally, hijacked user accounts are able to be detected by statistical ltering software support, and spam mails coming from these users can be blocked and the account owners can be informed. According to the test results, 99.4% of the spam mails were able to be stopped by the proposed method, and the false positive problem was able to be solved and a signicant decrease in the false negative percentages was ensured.

Trajectory analysis for user verification and recognition

For many computer activities, user verification is necessary before the system will authorize access. The objective of verification is to separate genuine account owners from intruders or miscreants. In this paper, we propose a general user verification approach based on user trajectories. A trajectory consists of a sequence of coordinated inputs. We study several kinds of trajectories, including on-line game traces, mouse traces, handwritten characters, and traces of the movements of animals in their natural environments. The proposed approach, which does not require any extra action by account users, is designed to prevent the possible copying or duplication of information by unauthorized users or automatic programs, such as bots. Specifically, the approach focuses on finding the hidden patterns embedded in the trajectories produced by account users. We utilize a Markov chain model with a Gaussian distribution in its transition to describe trajectory behavior. To distinguish between two trajectories, we introduce a novel dissimilarity measure combined with a manifold learned tuning technique to capture the pairwise relationship between the two trajectories. Based on that pairwise relationship, we plug-in effective classification or clustering methods to detect attempts to gain unauthorized access. The method can also be applied to the task of recognition, and used to predict the type of trajectory without the user’s pre-defined identity. Our experiment results demonstrate that, the proposed method can perform better, or is competitive to existing state-of-the-art approaches, for both of the verification and recognition tasks.