The 1st International Workshop on Privacy Algorithms in Systems (PAS)
PAS Workshop at CIKM'22
Tell Me More!

About

Today we face an explosion of data generation, ranging from health monitoring to national security infrastructure systems. More and more systems are connected to the Internet that collects data at regular time intervals. These systems share data and use machine learning methods for intelligent decisions, which resulted in numerous real-world applications (e.g., autonomous vehicles, recommendation systems, and heart-rate monitoring) that have benefited from it. However, these approaches are prone to identity thief and other privacy related cyber-security attacks. So, how can data privacy be protected efficiently in these scenarios? More dedicated efforts are needed to propose the integration of privacy techniques into existing systems and develop more advanced privacy techniques to address the complex challenges of multi-system connectivity and data fusion. Therefore, we propose the PAS at CIKM’22, which provides a venue to gather academic researchers and industry researchers/practitioners to present their research in an effort to advance the frontier of this critical direction of privacy algorithms in systems.

PAS at CIKM'22 provides a venue to gather the academia researchers and industry researchers/practitioners to present the recent progress of privacy algorithms in systems.


Topics of Interest

Recently privacy has been widely used in many scientific domains and everyday communications and systems. Even privacy regulations have been developed on a national and international level. Privacy topic affects all kinds of complex datasets such as text, video, audio, image, streaming, and graph format. They are produced by surveillance systems, home management systems, user tracking devices, data storage, communication systems, social networks, etc. Machine learning/decision making algorithmic systems have been widely adopted to facilitate efficient systems. As our ability to generate and collect data constantly increases unprecedentedly, the complex data we are facing in the modern era are becoming more and more diverse and large-scale. This raises privacy concerns for users, systems, and infrastructure, leading to more efforts to develop effective privacy preservation algorithms and deploy them efficiently for real-world applications.

This workshop aims to discuss the recent research progress of privacy algorithms in both theoretical foundations and practical applications for systems. We invite submissions that focus on recent advances in research/development of privacy algorithms and their applications. Theory and methodology papers are welcome from any of the following areas, including but not limited to:
  • Theory of privacy algorithms (e.g., differential privacy, local differential privacy, pan-privacy, data anonymization)
  • Privacy preservation of complex data (e.g., image, text, video, audio, streaming data, graph data) and data sharing
  • Privacy preservation decision making algorithms, machine and federated learning, transfer and semi-supervised learning, meta-learning
  • Privacy preservation in deep learning models (e.g., convolutional neural networks, graph neural networks, recurrent neural networks, transformer-based networks, etc.)
  • Benchmark analysis of privacy algorithms
  • Relation between privacy guarantee, fairness, and bias
  • Metrics for data privacy
  • Implementation of privacy policies and regulations in privacy algorithms
  • Privacy attacks on complex data and methods
and application papers focused on but not limited to:
  • Recommender Systems, Computer Vision, Natural Language Processing
  • Biomedical, Healthcare, Insurance
  • Cybersecurity, Financial security, Consumer protection
  • Transportation/Mobility networks
  • Cloud, Edge, and HPC systems


Important Dates

  • Submission deadline: August 29th, 2022
  • Notification of Acceptance: September, 15th, 2022
  • Camera-ready paper due: Septebmer, 30th, 2022
  • PAS at CIKM'22 Workshop day: October 21st, 2022

Submission Details

All submissions must be in PDF format and formatted according to the new ACM format published in ACM guidelines (e.g., using the ACM LaTeX template on Overleaf here) and selecting the "sigconf" sample. Submitted works will be assessed based on their novelty, technical quality, potential impact, and clarity of writing (and should be in English). For papers that primarily rely on empirical evaluations, the experimental settings and results should be clearly presented and repeatable. We encourage authors to make data and code available publicly when possible.

All submissions must be uploaded electronically to EasyChair at: Submission Page

NEWS: The CIKM’s OC has decided that each accepted paper must have at least one author with “in-person (non-student) workshop registration”, even if all the authors will only attend virtually. For more information, plase visit the conference website and the pricing page . Note that the fee is $225 for ACM/SIGWEB/SIGIR members and $300 for non-members.

For questions regarding submissions, please contact us at: cikm2022pas@easychair.org
Submissions can fall in one of the following categories:
  • Long research papers (5-10 pages)
  • Short research/application papers (2-4 pages)

Program


1:00 - 1:05 pm Welcome & Opening Remarks [Prof. Phillip S. Yu]
1:05 - 1:40 pm Keynote from Academia [Prof. Norman Sadeh]
1:40 - 2:20 pm Keynote from Industry & Academia [Prof. Graham Cormode]
2:20 – 3:00 pm Keynote from Academia [Prof. Dan Lin]
3:00 - 3:10 pm Coffee Break/Social Networking
3:10 – 3:50 pm Keynote from Industry [Dr. Harsha Nori]
3:50 – 4:50 pm Contributed Research Oral Talks [4 talks]
4:50 – 5:00 pm Final Remarks


Accepted Papers
  • Privacy policies robustness to reverse engineering.
    Aaron Kusne and Olivera Kotevska

  • STL-DP: Differentially Private Time Series Exploring Decomposition and Compression Methods.
    Kyunghee Kim, Minha Kim and Simon Woo

  • k-Means SubClustering: A Differentially Private Algorithm with Improved Clustering Quality.
    Devvrat Joshi and Janvi Thakkar

  • Privacy Amplification for Episodic Training Methods.
    Vandy Tombs, Olivera Kotevska and Steven Young

Confirmed Keynote Speakers

Graham Cormode

Professor

University of Warwick and Meta (UK)

Norman Sadeh

Professor

Carnegie Mellon University (USA)

Dan Lin

Professor

Vanderbilt University (USA)

Harsha Nori

Senior Data Scientist

Microsoft (USA)

Organization


Workshop Co-Chairs

Philip S. Yu

Distinguished Professor

University of Illinois Chicago

Olivera Kotevska

Research Scientist

Oak Ridge National Laboratory

Tyler Derr

Assistant Professor

Vanderbilt University




Additional Workshop Organizers

Proceedings Chair


Chris Stanley

Research Scientist

Oak Ridge National Laboratory

Web Chair


Yuying Zhao

PhD Student

Vanderbilt University