CB系统SA攻击算法重构函数出错

Question

我尝试执行以下链接中的附加代码： https://github.com/biometricsecurity/Preimage-attack-on-BTP-template 该代码旨在衡量 CB 系统的相似性攻击。我尝试运行 Biohahin 的示例，它运行时没有错误。我通过IoM功能改变了Biohash的功能，但重建功能不起作用。我需要你的帮助来解决问题。代码已附上。

提前致谢

function [randum] = random_IoM_edit(orig_length,Ndimension,Nprojection)


randum = randn(orig_length,Ndimension,Nprojection);

end


function [transformed_templates] = IoM_edit(opts)

persons=opts.nopersons;
for i=1:persons
    training_vector=opts.data(i,:);
 maxout_code_training_ind = [];
 for counter = 1:opts.Nprojection
            
            tmp_training= training_vector* opts.model(:,:,counter);
            [m_trainig ind_training] = max(tmp_training);
            maxout_code_training_ind = [maxout_code_training_ind, ind_training];
 end
 transformed_templates(i,:)=maxout_code_training_ind;
end




function [distance] = fitness_iom_edit(x, hashcode,opts)

 [transformed_data] = IoM_edit(opts);

distcc=[];
for a=1:size(hashcode,1)
    distcc=[distcc  1-matching_IoM(hashcode(a,:),transformed_data)];
end
distance=mean(distcc);


end

主要的mat文件是：

%clear all;
close all;
load('data\lfw\LFW_10Samples_insightface.mat')
load('data\lfw\LFW_label_10Samples_insightface.mat')
labels=ceil(0.1:0.1:158);

addpath('matlab_tools');
addpath_recurse("btp")
    opts.data= LFW_10Samples_insightface
    opts.Ndimension= 50;
    opts.Nprojection = 300;
    opts.nopersons=size(LFW_10Samples_insightface,1);
    opts.dX=size(LFW_10Samples_insightface,2);
    opts.model = random_IoM_edit(opts.dX,opts.Ndimension,opts.Nprojection);
    
    
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    %% facenet iom generate dataset
[transformed_data] = IoM_edit(opts);
    
    
    %scores = 1- pdist2(transformed_data,transformed_data,'Hamming');
    %hamming_gen_score = scores(labels'==labels);
    %hamming_gen_score = hamming_gen_score(find(hamming_gen_score~=1));
    %hamming_imp_score = scores(labels'~=labels);
    
    
    %[EER_HASH, mTSR, mFAR, mFRR, mGAR] =computeperformance(hamming_gen_score, hamming_imp_score, 0.001);  % isnightface 3.43 % 4.40 %
    reconstruct_x=zeros(158,512);
    
    %% reconstruct the first one
    for i=1:158
        disp(['reconstructing ',num2str(i)])
        to_retrieve_hash=transformed_data((i-1)*10+1,:); % first of the template are used to reconstruct
        %rng default % For reproducibility
        f_fitness = @(x)fitness_iom_edit(x,to_retrieve_hash,opts); % fitness function
         f_constr = []; 
         
        reconstruct_x(i,:) = reconstruct(f_fitness,f_constr,opts);  
    end
    
    
    save(['data/iomhashing_reconstructnoconstraint_',num2str(dimensions),'.mat'],'reconstruct_x');
    save(['data/iomhashing_eer_',num2str(dimensions),'.mat'],'EER_HASH');

我有机会通过花药IoM函数进行Biohashing，重建函数不构造所需的矩阵

Answer 1

我认为你面临的问题是用 IoM 替换 Biohashing 后 IoM 算法中的重建函数。由于重建函数不起作用，它可能与如何定义和使用适应度函数

fitness_iom_edit

（或者可能与如何重建或处理数据）有关。

我建议您检查您的输入尺寸并确保

reconstruct

功能符合要求。

其次，调试健身功能。

fitness_iom_edit

函数通过

matching_IoM

计算原始哈希码和新数据之间的距离。

第三，验证

reconstruct

函数，因为它可能需要修改才能与 IoM 配合使用。

您还应该确认

opts

结构的初始化对于 IoM 是正确的（包括

opts.model

）。

这里是一些调试代码：

function [distance] = fitness_iom_edit(x, hashcode, opts)
    [transformed_data] = IoM_edit(opts);
    
    distcc = [];
    for a = 1:size(hashcode, 1)
        dist = 1 - matching_IoM(hashcode(a, :), transformed_data);
        distcc = [distcc, dist];
    end
    
    distance = mean(distcc);
    
    % Debugging output
    disp('Fitness function results:');
    disp(['Distance: ', num2str(distance)]);
end

这是您编辑的脚本：

% Load data and labels
load('data\lfw\LFW_10Samples_insightface.mat')
load('data\lfw\LFW_label_10Samples_insightface.mat')

labels = ceil(0.1:0.1:158);

% Add necessary paths
addpath('matlab_tools');
addpath_recurse("btp");

% Set up options
opts.data = LFW_10Samples_insightface;
opts.Ndimension = 50;
opts.Nprojection = 300;
opts.nopersons = size(LFW_10Samples_insightface, 1);
opts.dX = size(LFW_10Samples_insightface, 2);
opts.model = random_IoM_edit(opts.dX, opts.Ndimension, opts.Nprojection);

% Generate transformed data
[transformed_data] = IoM_edit(opts);

% Initialize reconstructed data array
reconstruct_x = zeros(158, opts.dX);

% Reconstruct each template
for i = 1:158
    disp(['Reconstructing ', num2str(i)]);
    to_retrieve_hash = transformed_data((i-1)*10+1, :); % Get the hash to reconstruct
    
    % Fitness function for reconstruction
    f_fitness = @(x) fitness_iom_edit(x, to_retrieve_hash, opts);
    f_constr = []; 
    
    % Attempt reconstruction
    reconstruct_x(i,:) = reconstruct(f_fitness, f_constr, opts);  
end

% Save results
save(['data/iomhashing_reconstructnoconstraint_', num2str(opts.Ndimension), '.mat'], 'reconstruct_x');

这应该正确初始化您的数组。我目前不在测试这个的位置。如果有任何问题我会编辑帖子。