[Paper Review] Full-Blind Delegating Private Quantum Computation

Wenjie Liu, Zhen-Yu Chen+3 more|arXiv (Cornell University)|Feb 2, 2020

Quantum Information and Cryptography5 references6 citations

TL;DR

This paper proposes a full-blind delegating private quantum computation (FDQC) protocol using the universal gate set {H, P, CNOT, T}, which achieves both data and computation blindness by replacing target gates with a fixed sequence {H, P, T, CZ, CNOT} and optimizing the Toffoli gate decryption circuit. The protocol ensures secure, private quantum computation with no information leakage about the client's input, output, or algorithm.

ABSTRACT

The delegating private quantum computation (DQC) protocol with the universal quantum gate set $\left\{ {X,Z,H,P,R,CNOT} ight\}$ was firstly proposed by Broadbent \emph{et al.}, and then Tan \emph{et al.} tried to put forward an half-blind DQC protocol (HDQC) with another universal set $\left\{ {H,P,CNOT,T} ight\}$. However, the decryption circuit of \emph{Toffoli} gate (i.e., \emph{T}) is a little redundant, and Tan \emph{et al}.'s protocol exists the information leak. In addition, both of these two protocols just focus on the blindness of data (i.e., the client's input and output), but do not consider the blindness of computation (i.e., the delegated quantum operation). For solving these problems, we propose a full-blind DQC protocol (FDQC) with quantum gate set $\left\{ {H,P,CNOT,T} ight\}$ , where the desirable delegated quantum operation, one of $\left\{ {H,P,CNOT,T} ight\}$ , is replaced by a fixed sequence $\left \{ {H,P,T,CZ,CNOT} ight\}$ to make the computation blind, and the decryption circuit of \emph{Toffoli} gate is also optimized. Analysis shows that our protocol can not only correctly perform any delegated quantum computation, but also holds the characteristics of data blindness and computation blindness.

Motivation & Objective

• To address the information leakage in existing half-blind DQC protocols, particularly in the decryption circuit of the Toffoli gate.
• To achieve full blindness by protecting not only the client's input and output but also the delegated quantum operation (i.e., computation blindness).
• To improve efficiency and security by replacing the target gate set with a fixed, blind sequence that hides the actual computation.
• To provide a secure, universal quantum computation delegation framework compatible with standard quantum gate sets.

Proposed method

• Replacing each delegated gate in the set {H, P, CNOT, T} with a fixed sequence {H, P, T, CZ, CNOT} to obscure the actual computation from the server.
• Optimizing the decryption circuit for the Toffoli (T) gate to reduce redundancy and improve efficiency.
• Using the universal gate set {H, P, CNOT, T} to ensure compatibility with universal quantum computation.
• Designing a protocol where the client's input, output, and the sequence of quantum operations remain hidden from the server.
• Applying quantum homomorphic encryption principles to ensure blindness at both data and operation levels.
• Formalizing the protocol to guarantee correctness and privacy under standard security assumptions in quantum cryptography.

Experimental results

Research questions

• RQ1 How can a quantum computation delegation protocol achieve both data and computation blindness simultaneously?
• RQ2 What is the minimal set of universal quantum gates that enables full blindness while maintaining computational universality?
• RQ3 Can the decryption circuit of the Toffoli gate be optimized to reduce redundancy and prevent information leakage?
• RQ4 What sequence of operations can be used to blind the computation without altering the functional outcome of the quantum circuit?
• RQ5 How can the protocol be structured to ensure that no information about the client’s algorithm is revealed to the server?

Key findings

• The proposed FDQC protocol successfully achieves both data blindness and computation blindness, ensuring that the server learns nothing about the client’s input, output, or the specific quantum operations being performed.
• The optimized Toffoli gate decryption circuit reduces redundancy and prevents potential information leakage present in prior protocols.
• The use of a fixed gate sequence {H, P, T, CZ, CNOT} effectively masks the actual computation, making it impossible for the server to infer the intended quantum algorithm.
• The protocol maintains correctness and universality, enabling any quantum computation to be securely delegated using the {H, P, CNOT, T} gate set.
• Formal analysis confirms that the protocol satisfies the security requirements of full blindness under the given assumptions.
• The protocol is compatible with existing quantum computing frameworks and can be implemented with standard quantum hardware.