Vous êtes sur la page 1sur 45

Efficient Privacy Preserving Protocols for Visual Computation

Maneesh Upmanyu
Advisors: C. V. Jawahar , Anoop M. Namboodiri, Kannan Srinathan,
Center for Visual Information Technology Center for Security, Theory & Algorithmic Research IIIT- Hyderabad

IIIT Hyderabad

Security and Privacy of Visual Data


Broad Objective
Development of secure computational algorithms in computer vision and related areas.
To develop highly-secure solutions To develop computationally efficient solutions

To develop solutions to problems with immediate impact

IIIT Hyderabad

Project Web-Page: http://cvit.iiit.ac.in/projects/SecureVision

Research Directions
Private Content Based Image Retrieval (PCBIR) Blind Authentication: A Secure
Crypto-Biometric Verification Protocol
Feature vector (fquery)
Root Info Q1 A1 Q2 A2

fquery, f(A1) fquery, f(A2)

Efficient Privacy Preserving Video Surveillance

..

Publication: Maneesh Upmanyu, Anoop M. Namboodiri, K. Srinathan and C.V. Jawahar; Efficient Privacy Preserving Video Surveillance: Proceedings of the 12th International Conference on Computer Vision (ICCV 2009) Publication: Maneesh Upmanyu, Anoop M. Namboodiri, K. Srinathan and C.V. Jawahar; Blind Authentication - A Secure Crypto-Biometric Verification Protocol: Appears in IEEETransactions on Information Forensics and Security (IEEE-TIFS), June 2010
IIIT Hyderabad

Publication: Shashank J, Kowshik P, Kannan Srinathan and C.V. Jawahar; Private Content Based Image Retrieval; In Proceedings of Computer Vision and Pattern Recognition (CVPR 2008)

Our Security Goal


What is meant by Privacy?
Design protocols to limit the information leakage through what is learned in addition to the designated output.

What is the Adversary Model?


Semi-honest vs. Malicious adversary

Analysis outline:
Correctness Security Complexity
IIIT Hyderabad

Assumptions
Reliable and secure communication channel Players are passively corrupt, that is, honest but curious. Players are computationally bounded. Players do not collude.

IIIT Hyderabad

Thesis Objective
Traditional Approaches uses highly interactive protocols.
Limitation: massive datasets Example: Blind Vision

Paradigm Shift
Compute directly in encrypted domain.
Encrypt -> Communicate -> Compute -> Decrypt

Domain specific encryption schemes.


PKC is data independent and generic.

Can the paradigm be generic yet efficient?


IIIT Hyderabad

Contribution of Thesis
A method that provides provable security, while allowing efficient computations for generic vision algorithms have remained elusive.

IIIT Hyderabad

We show that, one can exploit certain properties inherent to visual data to break this seemingly impenetrable barrier.

Dilemma of Privacy vs. Accuracy

IIIT Hyderabad

What is Blind Authentication?


A biometric authentication protocol that does not reveal any:
information about the biometric samples to the authenticating server. information regarding the classifier, employed by the server, to the user or client

IIIT Hyderabad

Biometric Authentication System

IIIT Hyderabad

Primary Concerns in a Biometric System


Template Protection
Non-Repudiable

Network and Client-side Security


Revocability

IIIT Hyderabad

Previous Work

IIIT Hyderabad

A template protection scheme with provable security and acceptable recognition performance has thus far remained elusive. A.K. Jain, Eurasip 2008

Homomorphic Encryption
An encryption scheme using which some algebric operation , like addition or multiplication, can be directly done on the cipher text. Let x1 = 20 and x2 = 22, to compute x1+x2 = 42

Use an encryption scheme, for example E(x) = ex


Server stores E(x1) = e20 and E(x2) = e22 Compute using encrypted data y = E(x1) E(x2) = e20.e22 = e42 Decrypt z = D(y) = ln(y) z = D(y) ln (e42) = 42

IIIT Hyderabad

User Enrollment

Enrollment based on a trusted third party.


IIIT Hyderabad

Authentication using a Linear Kernel

IIIT Hyderabad

Extensions to Kernels & Neural Networks


Kernel based classifier uses a discriminating function like

Similarly, in Neural Network the basic units are for example perceptron or sigmoid

Model above functions as arithmetic circuits consisting of add and multiplication gates over a finite domain. Consider two encryptions E+ and E*
IIIT Hyderabad

Implementation and Analysis


Experiments designed to evaluate the efficiency and accuracy of proposed approach. For evaluation, an SVM based verifier based on clientserver architecture was implemented.
Accuracy: as no assumptions are made, accuracy remains same.
Verified this on various public domain (UCI, Statlog) datasets.

IIIT Hyderabad

Case study shows that matching using fixed length feature representation is comparable to variable length methods such as dynamic warping.

IIIT Hyderabad

Security, Privacy and Trust


Server Security
Template database security Hacker sitting in server

Client Security
Hacker has users key or biometric Passive attacks at client end

Network Security
IIIT Hyderabad

Network is susceptible to snooping attacks

Advantages of Blind Authentication


Fast and Provably Secure authentication without trading off accuracy. Supports generic classifiers such as Neural Network and SVMs.

Useful with wide variety of fixed-length biometrictraits.


Ideal for applications such as biometric ATMs, login from public terminals.
IIIT Hyderabad

Proposed Surveillance System

Plain Video
Captured by Camera

Encrypted Video
As seen by one of the Computational Servers

Processed Video
As seen by the Computational Server

Result Video
Received by Observer

How do we carry out surveillance


IIIT Hyderabad

on Randomized images ?

Motivation
Can we do surveillance without

seeing the original video ?

Ability to run video surveillance algorithms, completely in encrypted domain can address most

privacy concerns.

Existing methods are either too slow for surveillance


IIIT Hyderabad

applications or do not provide provable privacy.

Paradigm Shift
Trusted Third Party
(TTP) In practice, do not have the luxury of a trusted entity

Selective Encryption
(Smart Camera)
No provable privacy, costly and tedious to upgrade

Homomorphic Encryption (Doubly)


Computationally expensive

Traditionally Explored Paradigms

Secure Multiparty Computation (SMC)

Highly inefficient, High level of privacy, an overkill in practice

IIIT Hyderabad

We use the paradigm of secret sharing to achieve private and efficient surveillance.

Protocol in a nutshell
Propose a Cloud-Computing based solution using k>2 non-colluding servers

IIIT Hyderabad

Shatter Merge Compute Image Result

The camera splits each captured frame F, into k ( > 2 ) shares using pixel level shatter function: To carry out a aof basic operation f on the input image, eachby The results operations on the shares are integrated server blindly carries out the equivalent basic operation f on the observer using a merge function ( CRT), to obtain final its share. result. Each share is then sent to an independent server for processing.

Secret Sharing
A method of distributing a secret among a group of servers, such that:
Each server on its own has no meaningful information Secret is reconstructed only when all shares combine together

IIIT Hyderabad

Existing methods are highly inefficient Asmuth-Bloom overcomes this limitation by working in Residue Number System (RNS).

Example to do Addition in RNS


RNS ( m1 = 37, m2 = 49; M = m1 x m2 = 1813)
X = 973%(m1, m2) (x1, x2) = (11, 42) Y = 678%(m1, m2) (y1, y2) = (12, 41)

Shatter: f(x) = (x.S+h) mod mi


x1 = 11, y1 = 12 z1 = (x1 + y1) % m1 = (11+12) % 37 = 23 x2 = 42, y2 = 41

z2 = (x2 + y2) % m2 = (42+41) % 49 = 34

Merge: m(xi, mi) = CRT(xi, mi) /S


IIIT Hyderabad

CRT (z1, z2)


Z = 1651

Data Properties
While general purpose secure computation appears inherently complex and oftentimes impractical.
We show certain properties of the data can be used to ensure efficiency while ensuring privacy.

Following properties are of interest to us.



IIIT Hyderabad

Limited and Fixed Range Scale Invariant Approximate Nature Non-General Operands

Characteristics of the System


Preserve Privacy
Light weight Limited data expansion Secure Storage
Carry out surveillance on random looking images.

Encrypted domain representation should allow efficient computations.


Obfuscation process should not blow up the video data. Obfuscation should be provably secure to ensure security at un-trusted servers. Only authorized people should be able to recover original plain video.

IIIT Hyderabad

Reconstruction of data

Implementation Challenges
Representation of negative numbers: Use an Implicit sign representation. Use (0, M/2) as positive and rest as negative. Sign conversion is carried out using additive inversion of Z. Overflow and Underflow: Operations are valid and correct as long as range of data is (-M/2, M/2). Integer Division and Thresholding: RNS domain is finite and hence not all divisions are defined. Dividing integer A by B is defined as A/B = (ai.bi-1) mod mi
IIIT Hyderabad

Defining Equivalent operations: For every f(x), we need to define f`(x) such that merging f`(xi) would give f(x).

Experimental Results

IIIT Hyderabad

IIIT Hyderabad

Properties of the Protocol


Servers are un-trusted and the network may be insecure. Near loss-less (PSNR~51). data encoding Circumvent theoretical bounds. Extremely efficient over SMC Not only efficient, but also provably secure Scalable, inexpensive and generic, thus practical

No compromise in accuracy.

Inexpensive capture device, and a unidirectional data flow.


Negligible overheads to make private computation practical. Secure as long as servers do not collude.

IIIT Hyderabad

Our approach shows that privacy and efficiency co-exists in the domain of visual data

K-Means Clustering
Data clustering is one of the most important techniques for discovery of patterns in a dataset. K-Means clustering is a simple and extensively used technique that automatically partitions a dataset into k clusters.

IIIT Hyderabad

The technique becomes more effective with larger amount of data such as when multiple businesses share their data to carry out the clustering together. However, the data may contain sensitive information.

Secure K-Means Algorithms


Trusted Third Party (TTP) based solutions
Dwork et al. ( Crypto 2004) Very Efficient No TTP in Real World, Possible security compromise

Data Perturbation techniques


Stanley et al. (BSD 03), Kargupta et al. (ICDM 03) Negligible communication overhead Partial security, Non-invertible transformations used

Those employing Multiparty Computations


Vaidya et al. (KDD 03), Jha et al. (ESORICS 05) Wright et al. (KDD 05), Inan et al (DKE 07) Complete privacy Highly in-efficient

IIIT Hyderabad

Our Distributed Solution


We simulate TTP on a set of un-trusted servers over an insecure network.

IIIT Hyderabad

Secret Sharing is a method of distributing a secret among a group of servers.

Proposed Protocol
Protocol consists of two phases
Phase One: Secure Data Distribution Phase Two: Secure K-Means

Phase One: Secure Storage of data at servers


Selection of an optimal RNS. Shattering of the users private data. Privacy: Server stores only the shattered shares of data.

Phase Two: Secure K-Means


Initialization Lloyd Step Knowledge Revelation

IIIT Hyderabad

Phase Two: Secure K-Means


Clusters are initialized using the shattered shares Lloyd Step involves iteratively computing the closest centers in a Euclidean space
Secure protocols for division and comparison

Securely evaluate the termination criteria


Send the shattered cluster centers to users who uses the Merge function on it

Privacy: No information is leaked to the servers


Data for operations such as division secured using randomization Randomization done so as to secure against possible GCD and factorization based attacks
IIIT Hyderabad

Overview of the Protocol

IIIT Hyderabad

User 1

User 2

Analysis
Overheads calculated over the nave TTP based protocol. Division and Comparison operations introduce communication overhead.
Limited to one round per operation

Traditional approaches uses SMC for this.


Based on OT, a communicational intensive protocol. O(n2) communication overhead to multiply two vectors (length n)

Limited data expansion


Eg: 32bit data shattered into 5 shares requires 54bits while traditional SS requires 160bits.
IIIT Hyderabad

Algorithm Properties
We have proposed a highly secure framework using paradigm of secret sharing. Negligible overheads in simulating algebraic operations. Achieve efficiency by exploiting the data properties. Solution does not demand any trust and the clustering is carried out directly on the encrypted data.

IIIT Hyderabad

Conclusion
Broad Objective
Development of secure computational algorithms in computer vision and related areas.
To develop highly-secure solutions To develop computationally efficient solutions To develop solutions to problems with immediate impact

The traditional methods of ensuring privacy are communication and computation expensive. We show that domain specific knowledge can be incorporated to ensure efficiency while retaining privacy. Moreover, our methods do not trade off accuracy.
IIIT Hyderabad

Related Publications
Maneesh Upmanyu, Anoop M. Namboodiri, K. Srinathan and C.V. Jawahar; Blind Authentication - A Secure Crypto-Biometric Verification Protocol In IEEE-Transactions on Information Forensics and Security (IEEE-TIFS, June 2010) Efficient Biometric Verification in Encrypted Domain In Proceedings of 3rd International Conference on Biometrics (ICB 2009) Efficient Privacy Preserving Video Surveillance Proceedings of the 12th International Conference on Computer Vision (ICCV 2009) Efficient Privacy Preserving K-Means Clustering Proceedings of the Pacific Asia Workshop on Intelligence and Security Informatics (PAISI 2010)

IIIT Hyderabad

Thank you for your attention

IIIT Hyderabad

RNS & CRT


Residue Number System (RNS) is an integer using a set of smaller integers.
RNS is defined by a set of k integer constants. {m1, m2, m3, , mk}
Secret A is represented by k smaller integers. {a1, a2, a3, , ak} where

ai = A modulo mi

This representation is valid as long as 0 < A < M, where M is LCM of mis

Chinese Remainder Theorem (CRT) is the method of recovering the integer value from a given set of smaller integers.
Define Mi = M/mi
Compute ci = Mi x (Mi-1 mod mi) The above equation is always valid in our system, therefore unique solution exists

IIIT Hyderabad

Shatter & Merge Functions


Shatter function of the private data. : Compute and store the secret shares

Where xi is the ith secret share, and is a uniform randomness

Merge function

Given recovered using CRT

: Reconstruct the secret. for different primes Pis, secret is

IIIT Hyderabad

Vous aimerez peut-être aussi