Blind Vision

By Shai Avidan, Moshe Butman. 2006

131 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

NoPeek: Information leakage reduction to share activations in distributed deep learning (2020, methodology): “Similarly [42, 43] uses MPC schemes like oblivious transfer, secure millionaire, secure dot product for face matching with respect to a collection of sensitive surveillance footage images.”
Distributed learning of deep neural network over multiple agents (2018, background): “A more practical approach proposed in [14] involves sharing only SIFT and HOG features instead of the actual raw data.”
Machine Learning Classification over Encrypted Data (2015, methodology): “A face detection algorithm over encrypted data already exists [19], [20], so our construction here is not the first such construction, but it serves as a proof of functionality for our library.”
Handbook of Face Recognition, 2nd Edition (2011, background): “In particular if one party owns images and another party has, for instance a face detection algorithm algorithms such as “Blind Vision”[5] allow certain algorithmic operations to be carried out by the second party on the first party’s data without the data itself being made available.”
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics (2017, background): “Avidan and Butman [44] provided a secure protocol for machine learning.”
Privacy Preserving Image-Based Localization (2019, background): “Privacy-aware object recognition and biometrics have been studied in vision since Avidan and Butman [9, 10], who devised a secure face detection system.”
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service (2018, methodology): “Homomorphic encryption has been used to keep both input and result private from an executing server [3], [7].”
Efficient privacy preserving video surveillance (2009, background): “Our main achievement is an approach that achieves information theoretic privacy, while being extremely efficient over SMC.”
Privacy Preserving Image Queries for Camera Localization (2019, background): “Avidan and Butman [10, 11] were one of the first to study privacy-aware techniques for computer vision for the face detection task.”
Privacy-Preserving Face Recognition (2009, background): “…the combination of signal processing with cryptographic techniques in order to protect privacy is an active area of research [13]; among others, solutions for recognizing speech on encrypted signals [33] or image classiﬁcation and object recognition on encrypted images [37,2] have been proposed.”