Secure Personalization: Towards Trustworthy Recommender Systems* [1/16]

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=yrmqGB9xhpU


Duration: 1:12:23
64 views
1

Publicly-accessible adaptive systems such as recommender systems present a security problem. Attackers, who cannot be readily distinguished from ordinary users, may introduce biased data in an attempt to force the system to ΓÇ£adapt



Other Videos By Microsoft Research


2016-09-06War, Power, Strategy
2016-09-06Limits of Obfuscation
2016-09-06Effective Static Race Detection
2016-09-06Group Forming and Grassroots Organizing Technology
2016-09-06Building Trustworthy Mesh Networks: Why Security and Fault-Tolerance Must Be Considered Together
2016-09-06Privacy-Enhanced Personalization [1/2]
2016-09-06Atomics for a Real-time Virtual Machine
2016-09-06Not from Scratch: What the Fine Arts brings to HCI
2016-09-06From Personal Computers to Personal Information Environments
2016-09-06An Introduction to Chapel: Cray Cascade's High-Productivity Language
2016-09-06Secure Personalization: Towards Trustworthy Recommender Systems* [1/16]
2016-09-06Computer Science for the future
2016-09-06GeoDec: Enabling Geospatial Decision Making
2016-09-0610 Rules for Strategic Innovators
2016-09-06Which Supervised Learning Method Works Best for What?  An Empirical Comparison
2016-09-06Using ACTIVboard In Interactive Presentations
2016-09-06Secure Trusted Overlay Networks for Robust Privacy-Protecting Communication
2016-09-06Dialogue Session: Worklife Balance and the Retention of Talent
2016-09-06From textons to parts: Local image features for texture and object recognition
2016-09-06Efficient Actions in Dynamic Auction Environment
2016-09-06Two Network Coding Talks for the price of one: Security, Low Complexity


Tags:
microsoft research