Cyberbullying is a growing problem affecting more than half of all American teens. The main goal of this paper is to investigate fundamentally new approaches to understand and automatically detect and predict incidents of cyberbullying in Instagram, a media-based mobile social network. In this work, we have collected a sample data set consisting of Instagram images and their associated comments. We then designed a labeling study and employed human contributors at the crowd-sourced CrowdFlower website to label these media sessions for cyberbullying. A detailed analysis of the labeled data is then presented, including a study of relationships between cyberbullying and a host of features such as cyberaggression, profanity, social graph features, temporal commenting behavior, linguistic content, and image content. Using the labeled data, we further design and evaluate the performance of classifiers to automatically detect and predict incidents of cyberbullying and cyberaggression.

This paper describes an INtrusion-tolerant routing protocol for wireless SEnsor NetworkS (INSENS). INSENS constructs forwarding tables at each node to facilitate communication between sensor nodes and a base station. It minimizes computation, communication, storage, and bandwidth requirements at the sensor nodes at the expense of increased computation, communication, storage, and bandwidth requirements at the base station. INSENS does not rely on detecting intrusions, but rather tolerates intrusions by bypassing the malicious nodes. An important property of INSENS is that while a malicious node may be able to compromise a small number of nodes in its vicinity, it cannot cause widespread damage in the network. A prototype implementation in the ns2click simulator is presented to demonstrate and assess INSENS's tolerance to malicious attacks launched by intruder nodes in random and grid topologies.

ABSTRACT

he mobile social networking revolution is upon us and could have as profound an effect in enriching local social interaction as the Internet has had in enriching online information access and discourse. The key observation in this article is that the explosive phenomenon of online social networks can be harnessed using mobile devices to answer the compelling question that frequently appears in local social contexts: "Who's that?" It is often the case that people want to find out more about those who are around them; for example, who is that speaking to a group of people in a corner of the room, or who is that who just walked into the room? Standard solutions include asking those around you, looking at name tags, introducing yourself, and so on, none of which leverage the power of technology to help answer these compelling questions and thereby enrich the social interaction.Online social networks have exploded in popularity [1-3]. As of December 2007, Facebook had over 59 million users [4]. It is estimated that over 85 percent of four-year college students have a Facebook profile, presenting a very usable penetration rate and providing an incredible resource for applications that might leverage this data. These online social networks provide a wealth of personal contextual information, including name, picture, contact information, gender, relationship status/interests, activities/hobbies, musical preferences, literature interests, group membership, and, of course, friendship information concerning user interconnection. Social networks provide a variety of mechanisms for users to share these rich sets of contextual data with other users, including searching for other users with similar interests, as well as a means to establish and maintain communication with other users. Social networks can be seen as a natural evolution of the Internet, where the first big wave facilitated a person's access to information; for example, Web servers and peer-topeer networks providing news and information content, as well as ways to buy products, whereas this next big wave is focused on facilitating person-to-person communication.WhozThat is motivated by the idea that bringing this rich contextual information from online social networks into the real world of local human interactions substantially enriches local social interaction. Imagine if you knew more about the people around you in a social gathering, such that you could more easily strike up a conversation with someone with whom you were interested in talking. By being informed via mobile technology of the identity of the person with whom you are seeking to interact and consulting information obtained from that person's public social networking profile, you could more easily initiate a conversation, perhaps introducing yourself and saying, "I noticed we have a shared interest in this hobby or that cause." The ability of mobile social networking (MoSoNet) technology to substantially lower the barriers to social discourse by minimizing unfamiliarity could revolutionize human soc...

No abstract

Group recommendation, which makes recommendations to a group of users instead of individuals, has become increasingly important in both the workspace and people's social activities, such as brainstorming sessions for coworkers and social TV for family members or friends. Group recommendation is a challenging problem due to the dynamics of group memberships and diversity of group members. Previous work focused mainly on the content interests of group members and ignored the social characteristics within a group, resulting in suboptimal group recommendation performance.In this work, we propose a group recommendation method that utilizes both social and content interests of group members. We study the key characteristics of groups and propose (1) a group consensus function that captures the social, expertise, and interest dissimilarity among multiple group members; and (2) a generic framework that automatically analyzes group characteristics and constructs the corresponding group consensus function. Detailed user studies of diverse groups demonstrate the effectiveness of the proposed techniques, and the importance of incorporating both social and content interests in group recommender systems.

No abstract

Typical packet traffic in a sensor network reveals pronounced patterns that allow an adversary analyzing packet traffic to deduce the location of a base station. Once discovered, the base station can be destroyed, rendering the entire sensor network inoperative, since a base station is a central point of data collection and hence failure. This paper investigates a suite of decorrelation countermeasures aimed at disguising the location of a base station against traffic analysis attacks. A set of basic countermeasures is described, including hop-by-hop reencryption of the packet to change its appearance, imposition of a uniform packet sending rate, and removal of correlation between a packet's receipt time and its forwarding time. More sophisticated countermeasures are described that introduce randomness into the path taken by a packet. Packets may also fork into multiple fake paths to further confuse an adversary. A technique is introduced to create multiple random areas of high communication activity called hot spots to deceive an adversary as to the true location of the base station. The effectiveness of these countermeasures against traffic analysis attacks is demonstrated analytically and via simulation using three evaluation criteria: total entropy of the network, total overhead/energy consumed, and the ability to frustrate heuristic-based search techniques to locate a base station.