Goto

Collaborating Authors

''Will Check-in for Badges'': Understanding Bias and Misbehavior on Location-Based Social Networks

AAAI Conferences

Social computing researchers are using data from location-based social networks (LBSN), e.g., "Check-in" traces, as approximations of human movement. Recent work has questioned the validity of this approach, showing large discrepancies between check-in data and actual user mobility. To further validate and understand such discrepancies, we perform a crowdsourced study of Foursquare users that seeks to a) quantify bias and misrepresentation in check-in datasets and the impact of self-selection in prior studies, and b) understand the motivations behind misrepresentation of check-ins, and the potential impact of any system changes designed to curtail such misbehavior. Our results confirm the presence of significant misrepresentation of location check-ins on Foursquare. They also show that while "extraneous" check-ins are motivated by external rewards provided by the system, "missing" check-ins are motivated by personal concerns such as location privacy. Finally, we discuss the broader implications of our findings to the use of check-in datasets in future research on human mobility.


CheckNet: Secure Inference on Untrusted Devices

arXiv.org Machine Learning

We introduce CheckNet, a method for secure inference with deep neural networks on untrusted devices. CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted devices to 1) ensure the inference has actually been performed, and 2) ensure the inference has not been manipulated by an attacker. CheckNet is completely transparent to the third party running the computation, applicable to all types of neural networks, does not require specialized hardware, adds little overhead, and has negligible impact on model performance. CheckNet can be configured to provide different levels of security depending on application needs and compute/communication budgets. We present both empirical and theoretical validation of CheckNet on multiple popular deep neural network models, showing excellent attack detection (0.88-0.99 AUC) and attack success bounds.


Facebook's Safety Check Is Now A Permanent Feature, Gets Own Dedicated Tab

International Business Times

Facebook's Safety Check is now a permanent feature on the social networking site. It has also gotten its own dedicated tab within the Facebook app, making it easier for users to alert their friends and family about their safety during times of calamity. "Safety Check helps our community let loved ones know they are safe during a crisis, find and give help, as well as learn more about a crisis," Facebook said on its Disaster Response page. "There's now a single place to go to see where Safety Check has recently been activated, get the information you need and potentially be able to help affected areas." The company also shared a photo of how the new Safety Check feature will work, and it looks like a new version of the News Feed.


Location3: How Users Share and Respond to Location-Based Data on Social

AAAI Conferences

In August 2010 Facebook launched Places, a location-based service that allows users to check into points of interest and share their physical whereabouts with friends. The friends who see these events in their News Feed can then respond to these check-ins by liking or commenting on them. These data consisting of the places people go and how their friends react to them are a rich, novel dataset. In this paper we first analyze this dataset to understand the factors that influence where users check in, including previous check-ins, similarity to other places, where their friends check in, time of day, and demographics. We show how these factors can be used to build a predictive model of where users will check in next. Then we analyze how users respond to their friends’ check-ins and which factors contribute to users liking or commenting on them. We show how this can be used to improve the ranking of check-in stories, ensuring that users see only the most relevant updates from their friends and ensuring that businesses derive maximum value from check-ins at their establishments. Finally, we construct a model to predict friendship based on check-in count and show that cocheck-ins has a statistically significant effect on friendship.


Chang

AAAI Conferences

In August 2010 Facebook launched Places, a location-based service that allows users to check into points of interest and share their physical whereabouts with friends. The friends who see these events in their News Feed can then respond to these check-ins by liking or commenting on them. These data consisting of the places people go and how their friends react to them are a rich, novel dataset. In this paper we first analyze this dataset to understand the factors that influence where users check in, including previous check-ins, similarity to other places, where their friends check in, time of day, and demographics. We show how these factors can be used to build a predictive model of where users will check in next. Then we analyze how users respond to their friends' check-ins and which factors contribute to users liking or commenting on them. We show how this can be used to improve the ranking of check-in stories, ensuring that users see only the most relevant updates from their friends and ensuring that businesses derive maximum value from check-ins at their establishments. Finally, we construct a model to predict friendship based on check-in count and show that cocheck-ins has a statistically significant effect on friendship.