PPMLP CCS 2020: Privacy Preserving Machine Learning in Practice At ACM CCS 2020 Orlando, FL, United States, November 9, 2020 |
Conference website | https://sci-workshops.alipay.com/CCS2020 |
Submission link | https://easychair.org/conferences/?conf=ppmlpccs2020 |
Submission deadline | July 27, 2020 |
With the rapid development of technology, user data is becoming ubiquitous. User privacy and data security are drawing much attention over the recent years, especially with the European Union’s General Data Protection Regulation (GDPR) and other national laws coming into force. On one hand, from the customers' perspective, how to protect user privacy while making use of customers’ data is a challenging task. On the other hand, data silos are becoming one of the most prominent issues for the society. From the business’ perspective, how to bridge these isolated data islands to build better AI systems while meeting the data privacy and regulatory compliance requirements has imposed great challenges to the traditional machine learning paradigm.
Academic researchers from different areas have proposed multiple ideas to attack the aforementioned challenges from different perspectives. Researchers and engineers in industries also implement various improvements on the internal AI systems for privacy and security enhancement. However, we need more opportunities to connect researchers from different backgrounds and domains together to exchange the problem formulations in practice and research advances in different principals.
The workshop on Privacy Preserving Machine Learning in Practice (PPMLP) includes but is not limited to the following techniques and applications:
-
Secure multi-party computation techniques (e.g., secret sharing and garbled circuit)
-
Homomorphic encryption techniques
-
Trusted execution environment (TEE) based approaches
-
Centralized and decentralized protocols for learning on encrypted data
-
Differential privacy
-
Collaborative learning / federated learning
-
(Privacy-preserving) transfer learning
-
Adversarial attacks and defenses
-
Solutions to database security in industries
-
Privacy-preserving industrial-scale AI solutions, especially for
Fintech, such as:
-
Multi-party secure fraud detection
-
Privacy-preserving recommendation
-
Privacy-preserving marketing/retailing
-
Privacy-preserving crowdsourcing/mobile crowdsourcing
-