Collaborative filtering with privacy

By John F. Canny. 2002

542 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

Privacy-Preserving Ridge Regression on Hundreds of Millions of Records (2013, background): “Some approaches use protocols based on secret sharing [8], [45]– [47] while others use additive homomorphic encryption (for horizontally partitioned data) [48].”
Preventing shilling attacks in online recommender systems (2005, background): “We think that zero-knowledge attacks such as the Random Bot are particularly interesting, since for the other attacks, recommender systems administrators could increase the privacy of user profiles using cryptographic means [6, 10, 2], thus falling back to the zero-knowledge ones.”
P4P: Practical Large-Scale Privacy-Preserving Distributed Computation Robust against Malicious Users (2010, methodology): “Our scheme supports any iterative algorithms whose(t + 1)-th update can be expressed as I(t+1) = f( n ∑ i=1 d (t) i , I (t)) whered(t)i = g(ai, I (t)) ∈ Zmφ is an m-dimensional data vector for useri computed locally.”
The Economics of Personal Data and the Economics of Privacy (2010, background): “…privacy (Adar and Huberamn, 2001), leverage the power of recommender systems and collaborative filtering without exposing individual identities Canny (2002), or even executing calculations in encrypted spaces (Gentry, 2009), opening the doors for novel scenarios of privacy preserving data…”
ItemRank: A Random-Walk Based Scoring Algorithm for Recommender Engines (2007, methodology): “Many different recommending algorithms have been proposed in literature, for example there are techniques based on Bayesian networks [Breese et al., 1998], Support Vector Machines [Grcar et al., 2005] and factor analysis [Canny, 2002].”
Practical Privacy Preserving POI Recommendation (2020, methodology): “The second type is based on cryptography techniques [2, 6, 20, 42, 44].”
Reversible Image Watermarking Using Interpolation Technique (2010, unknown): “Once the same (cid:3)(cid:4) , (cid:3)(cid:10) , (cid:5)(cid:4) , and (cid:5)(cid:10) are known, embedded data can be extracted through (cid:8) (cid:0) (cid:19) (cid:9) (cid:0) (cid:0) (cid:0) (cid:3)(cid:4) (cid:15)(cid”
Towards a More Reliable Privacy-preserving Recommender System (2017, background): “without Additional Information without 3rd Party Existence Protected Model Protected Value Protected [5] √ √ √ √ [13] √ √ √ √ [14] √ √ √ [10] √ √ √ [7] √ √ √ [11] √ √ √”
A Simple and Efficient Federated Recommender System (2019, methodology): “Among the extensive research to secure privacy in recommender systems are methods that include cryptography algorithms [7, 23] and differential privacy [4, 20].”
Differentially Private Matrix Factorization (2015, background): “What’s worse, we have no way to guarantee that recommenders do not abuse user data for financial benefits [Canny, 2002; Nikolaenko et al., 2013].”
Scalable and Private Media Consumption with Popcorn (2016, background): “Again, we believe that this limitation is not fundamental [16, 21, 23, 51, 60, 63].”
Bug isolation via remote program sampling (2003, background): “Recent work on protecting privacy and preventing abuse in collaborative filtering systems may also be applicable [9, 11].”
Privacy-Preserving Inter-database Operations (2004, methodology): “Canny has proposed methods for privacy-preserving collaborative filtering [6, 7].”
Applying Differential Privacy to Matrix Factorization (2015, background): “Canny proposed a decentralized storage of user profiles, which requires the adversary to compromise multiple systems when attacking a distributed recommender [3].”