Privacy-Preserving IR: When Information Retrieval Meets Privacy and
Security (*PIR Workshop 2014*)
At *SIGIR* *2014*, July 11 2014, Gold Coast, Australia


Call for Papers (2 & 6 pages)

**Submission deadline: May 19th, 2014**

With the emergence of online social networks and the growing popularity of
digital communication, more and more information about individuals is
becoming available on the Internet. While much of this information is not
sensitive, it is not uncommon for users to publish sensitive information
online, especially on social networking sites. The availability of this
publicly accessible and potentially sensitive data can lead to abuse and
expose users to stalking and identity theft. An adversary can digitally
"stalk" a victim (a Web user) and discover as much information as possible
about the victim, either through direct observation of posted information
or by inferring knowledge using simple inference logic.

Information retrieval and information privacy/security are two fast-growing
computer science disciplines. Information retrieval provides a set of
information seeking, organization, analysis, and decision-making
techniques. Information privacy/security defends information from
unauthorized or malicious use, disclosure, modification, attack, and
destruction. The two disciplines often appear as two areas with opposite
goals: one is to seek information from large amounts of materials, the
other is to protect (sensitive) information from being found out. On the
other hand, there are many synergies and connections between these two
disciplines. For example, information retrieval researchers or
practitioners often need to consider privacy or security issues in
designing solutions of information processing and management, while
researchers in information privacy and security often utilize information
retrieval techniques when they build the adversary models to simulate how
the adversary can actively seek sensitive information. However, there have
been very limited efforts to connect the two important disciplines.

In addition, due to lack of mature techniques in privacy-preserving
information retrieval, concerns about information privacy and security have
become serious obstacles that prevent valuable user data to be used in IR
research such as studies about query logs, social media, tweets, session
analysis, and medical record retrieval. For instance, the recent TREC
Medical Record Retrieval Tracks are halted because of the privacy issue and
the TREC Microblog Tracks could not provide participants with a standard
testbed of tweets for system development. The situation needs to be
improved in a timely manner. All these motive us to propose this
"privacy-preserving IR" workshop in SIGIR.

The workshop welcome submissions on topics included but are not limited to:

- Searching and Protecting Private or Sensitive Information: there is a
large amount of private and     sensitive digital information in text and
other media. It is important to identify, utilize, anonymize and protect
the information;

- Novel Information Retrieval Techniques for Information Privacy/Security
Application: new information retrieval or machine learning techniques need
to be designed that fit the practice of applications in information privacy
and security;

- Protecting User Privacy in Search, Recommendation and Beyond: much damage
can be caused as users can be identified in AOL query log data and Neflix
log data, it is important to develop effective and efficient solutions to
protect users' privacy in information retrieval applications;

- Information Exposure Detection: new information retrieval and natural
language processing technologies are needed to quickly identify components
and/or attributes of a user's online public profile that may reduce the
user's privacy, and warn one's vulnerability on the Web;

- Private Information Retrieval Techniques for Enabling Location Privacy in
Location-Based Services: data about a user's location and historical
movements can potentially be gathered by a third party who takes away the
information without the awareness of the service providers and the users,
how location-based services and recommender systems interact with Location
Obfuscation techniques and other Privacy-Enhancing Technologies;

- Private Information Retrieval (PIR): PIR schemes are cryptographic
protocols designed to safeguard the privacy of database users; they allow
clients to retrieve records from public databases while completely hiding
the identity of the retrieved records from database owners.

Paper Submissions
The submissions will be peer reviewed and must be formatted according to
the ACM SIG proceedings template (
http://www.acm.org/sigs/publications/proceedings-templates ). Papers should
be in PDF and submitted through EasyChair (
We welcome both Long papers and Short papers:
- Long Paper: A maximum of *6* pages, including graphs, figures, and
references. Accepted long papers will need to give a 15-minute oral
- Short Paper: A maximum of *2* pages, including graphs, figures, and
references. Accepted short papers will have a 5-minute oral presentation.
Submissions will be reviewed by members of the workshop program committee.
Accepted papers will be included in the SIGIR 2014 Privacy-Preserving IR
(PIR) Workshop proceedings.

Important Dates
Submission Deadline: Monday, May 19th 2014 (23:59UTC-11; Samoa time zone)
Acceptance Notifications: Monday, June 9th 2014
Camera-ready Deadline: Friday, June 20th 2014
Workshop: Friday, July 11th 2014

Workshop Organizers
Luo Si, Purdue University, USA
Grace Hui Yang, Georgetown University, USA