Privacy Dynamics: Learning Privacy Norms for Social Software

Privacy violations in online social networks (OSNs) often arise as a result of users sharing information with unintended audiences. One reason for this is that, although OSN capa- bilities for creating and managing social groups can make it easier to be selective about recipients of a given post, they do not provide enough guidance to the users to make informed sharing decisions. In this paper we present Pri- vacy Dynamics, an adaptive architecture that learns privacy norms for dierent audience groups based on users' sharing behaviours. Our architecture is underpinned by a formal model inspired by social identity theory, a social psychology framework for analysing group processes and intergroup re- lations. Our formal model comprises two main concepts, the group membership as a Social Identity (SI) map and privacy norms as a set of con ict rules. In our approach a privacy norm is specied in terms of the information objects that should be prevented fromowing between two con icting social identity groups. We implement our formal model by using inductive logic programming (ILP), which automati- cally learns privacy norms. We evaluate the performance of our learning approach using synthesised data representing the sharing behaviour of social network users.

[1]  Maeve Duggan,et al.  Social Media Update 2016 , 2016 .

[2]  Jure Leskovec,et al.  Discovering social circles in ego networks , 2012, ACM Trans. Knowl. Discov. Data.

[3]  H. Tajfel,et al.  An integrative theory of intergroup conflict. , 1979 .

[4]  Yang Wang,et al.  From Facebook Regrets to Facebook Privacy Nudges , 2013 .

[5]  Marius Thomas Lindauer,et al.  Potassco: The Potsdam Answer Set Solving Collection , 2011, AI Commun..

[6]  E. Litt Knock, Knock. Who's There? The Imagined Audience , 2012 .

[7]  Stephen Muggleton,et al.  Inductive Logic Programming , 2011, Lecture Notes in Computer Science.

[8]  Chiaki Sakama,et al.  Brave induction: a logical framework for learning from incomplete information , 2009, Machine Learning.

[9]  Martin Gebser,et al.  Answer Set Solving in Practice , 2012, Answer Set Solving in Practice.

[10]  Krysia Broda,et al.  Inductive Learning of Answer Set Programs , 2014, JELIA.

[11]  Jeffrey O. Kephart,et al.  The Vision of Autonomic Computing , 2003, Computer.

[12]  Alessandra Russo,et al.  Inductive Logic Programming in Answer Set Programming , 2011, ILP.

[13]  Robin I. M. Dunbar Neocortex size as a constraint on group size in primates , 1992 .

[14]  Krysia Broda,et al.  Learning Through Hypothesis Refinement Using Answer Set Programming , 2013, ILP.

[15]  Antti Oulasvirta,et al.  All My People Right Here, Right Now: management of group co-presence on a social networking site , 2009, GROUP.

[16]  Berker Agir,et al.  Adaptive information-sharing for privacy-aware mobile social networks , 2013, UbiComp.

[17]  Helen Nissenbaum,et al.  Privacy and contextual integrity: framework and applications , 2006, 2006 IEEE Symposium on Security and Privacy (S&P'06).

[18]  Pinar Yolum,et al.  Negotiating Privacy Constraints in Online Social Networks , 2015, CARE/MFSC@AAMAS.

[19]  Danah Boyd,et al.  I tweet honestly, I tweet passionately: Twitter users, context collapse, and the imagined audience , 2011, New Media Soc..

[20]  H. Nissenbaum Privacy as contextual integrity , 2004 .

[21]  Natalia Criado,et al.  Adaptive Conflict Resolution Mechanism for Multi-party Privacy Management in Social Media , 2014, WPES.

[22]  Norman M. Sadeh,et al.  User-Controllable Learning of Location Privacy Policies With Gaussian Mixture Models , 2011, AAAI.

[23]  Natalia Criado,et al.  Implicit Contextual Integrity in Online Social Networks , 2015, Inf. Sci..

[24]  Dominic Abrams,et al.  Intergroup Relations: Essential Readings , 2001 .

[25]  Norman Sadeh,et al.  Understandable Learning of Privacy Preferences Through Default Personas and Suggestions , 2011 .

[26]  Kristen LeFevre,et al.  Privacy wizards for social networking sites , 2010, WWW '10.

[27]  A. Plastino,et al.  Unravelling the size distribution of social groups with information theory in complex networks , 2009, 0905.3704.

[28]  Pinar Yolum,et al.  PROTOSS: A Run Time Tool for Detecting Privacy Violations in Online Social Networks , 2012, 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.