DTL 2017


DTL 2017 Travel Grants

DTL 2017 Travel Grants

A note from the DTL Research Commitee Chairs, Balachander Krishnamurthy and Nikolaos Laoutaris:

All the 45 submissions received were discussed extensively online and 11 of them were further vetted in the live PC meeting.

For a proposal to make it as a finalist, it had to describe a novel working end-user software or a collection platform that improves data/algorithm transparency and/or privacy.

Proposals got bonus points if they targeted priority areas for this year or if they built constructively upon earlier DTL tools.

9 submissions out of 11 discussed in the PC meeting were presented in no particular order to the DTL board on Friday June 23. The board selected 6 submissions to fund.

We thank the PC for their hard work in reviewing, extensive online discussions and participating in the PC meeting. We thank the board for their pointed questions and selecting submissions that we all hope will generate transparency software. We thank all the submittees for their time.

We expect the grant awardees to complete their software, make the code and data available, acknowledge the support from DTL, and present their results with a demo at DTL next year.

The following projects have received a travel grant to attend DTL Conferences in Barcelona and will be able to present their projects in a poster session.


Natural Privacy Controls for Voice-based Smart Assistants

Florian Schaub (University of Michigan); Manikandan Kandadai Venkatesh (University of Michigan)

Voice-based smart assistants, such as Amazon Alexa and Google Home are becoming increasingly popular. Despite their benefits, voice based smart assistants pose substantial and novel privacy risks, because they could act as always-on listening devices in people’s homes and workplaces. While these systems offer basic privacy controls, it is not clear whether they properly address users’ privacy concerns and enable effective privacy management. Privacy of voice-based smart assistants has not been studied in detail so far. This project will (1) study privacy concerns and configuration issues with voice-based assistants and (2) develop natural privacy controls for voice-based smart assistants that enable more context-aware and fine-grained privacy control and transparency without overburdening users with extensive privacy management functionality.

Pri-Assistant: A tool for detecting privacy leaks from personal assistant commands

Arti Ramesh (State University of New York, Binghamton); Yan Wang (State University of New York, Binghamton), Gissella María Bejarano Nicho (State University of New York, Binghamton), Lei Jiaxin (State University of New York, Binghamton)

Personal/home assistants such as Amazon Alexa/Echo, Google home/now, Apple Siri and Microsoft Cortana are becoming increasingly common in households across the globe. With the proliferation of these devices, there is also a corresponding increase in privacy concern around the data collected by these devices and leakage of personally identifiable information (PII) should the data be intercepted. In this work, we propose to build a machine learning prediction framework to analyze the commands given to the assistants to predict possible PII leakage. We further propose to integrate the output of our framework into an easy-to-use end-user mobile application which users can utilize to self-monitor their commands and periodically purge PII revealing commands. Our tool is intended as an after-use purge tool, hence minimizing privacy concerns while simultaneously maximizing user experience with the assistants.

A Nutritional Label for rankings

Julia Stoyanovich (Drexel University); Ke Yang (Drexel University)

Algorithmic decisions often result in scoring and ranking individuals, to determine credit worthiness, desirability for college admissions and employment, and attractiveness as dating partners. As is often the case with algorithmic processes, rankers can, and do misbehave | they discriminate against individuals and members of protected groups, and violate privacy. Additionally, ranked results are often unstable | small changes in the input data or in the ranking methodology may lead to drastic changes in the ranked output, making the result uninformative. Rankers tend to be opaque, making discrimination, lack of stability, and privacy violations difficult to detect. Despite the ubiquity of rankers, there is, to the best of our knowledge, no technical work that focuses on making rankers transparent. The goal of our project is to  ll this gap.

In this project we will build Ranking Facts, a Web-based application that generates a nutritional label for rankings. Our nutritional label will explain ranked outputs to a user, demystifying the ranking process and its results. This work will give transparency tools to every-day Web users, designers of ranking schemes and regulators, while also making critical contributions to computer science. All outcomes of this work will be made publicly available in the open source.

Moving forward: understanding how location data influences personalized content in the mobile context

Sébastien Gambs (Université du Québec à Montréal (UQAM)); Antoine Boutet (INSA-Lyon)

This project aims to at increasing the transparency of targeted advertising and personalized services in the specific context of mobile computing. More precisely, we propose to investigate how the location data of users is processed for generating personalized contents and advertisements for mobile devices. To achieve this objective, we propose to develop two complementary axes. The first axis aims at raising the user awareness on the potential sensitivity associated to the collection and the exploitation of location data. More precisely, we will develop a mobile application analyzing the location tracking to inform users with respect to the information (e.g., mobility patterns, interests, activities, …) that can be inferred from the gathered data. The second axis will conduct an in-depth analysis on how the location data is processed to produce the personalized service. To realize this, we will explore the impact of mobility on personalization and discrimination.

The X-PAT Files: Identifying and Cataloging Cross-platform Advertising and Tracking Services

Rishab Nithyanand (Stony Brook University); Phillipa Gill (UMass – Amherst)

Third-party services form an integral part of the Web and mobile ecosystems: they allow customized services based on user data, enable monetization of services, and facilitate social network integration. However, the prevalence and activities of these services remains largely opaque. While efforts have been made to reveal the behavior of third party trackers in the Web and mobile contexts, the extent to which third party services are able to link information between Web and mobile applications remains unknown.

Our high-level goal is to develop an ecosystem of tools and datasets to increase transparency in this space. We envision a suite of tools to empower users to understand and control how their data is used by third party trackers across platforms. Using these tools and controlled experiments we will also create data sets and information that can help inform policy makers and advocacy groups in this space. Concretely, we plan to leverage ICSI Haystack/Lumen [2] and OpenWPM [1] to develop techniques to identify applications and third parties that perform tracking across platforms. This investigation will allow us to characterize the prevalence and activities of cross platform trackers. Building off of these tools we will also develop a suite of tools that will allow users to understand and control how their data is used by these services.

DTL 2018 text logo

You can now register to participate at the Hackathon organized by LUCA. Check the projects awarded with a Call for Tools grant. Subscribe to our Newsletter to stay up to date with our news and activities.

This website uses cookies to improve user experience. By using our website you consent to all cookies in accordance with our Cookie Policy.

OK More information