static void Main(string[] args)
{
/////////////////////////////////////////////////////////////////////////////////////////
// Below are some examples of possible experiments and functions you may wish to call. //
/////////////////////////////////////////////////////////////////////////////////////////
// Morph an english word dictionary into a password database where 10% of passwords have a number
// ToyProblemUtil.MorphEnglish(ENGLISH_WORDS, MORPHED_ENGLISH_WORDS);
// Morph an english word dictionary into a password database where all passwords are at least 8 characters
// and contain at least one number
// ToyProblemUtil.MorphEnglish(ENGLISH_WORDS, FORCED_MORPHED_ENGLISH_WORDS, requireDigit: true, minLength: 8);
// Train on the no-rule morphed english words db and evolve against the morphed english db with
// the digit and length creation rules enforced.
// RunExperiment(MORPHED_ENGLISH_WORDS, MORPHED_SEED_FILE, MORPHED_CONFIG_FILE, MORPHED_RESULTS_FILE, false);
//Train on the phppb dataset and evolve against the rockyou dataset
//RunExperiment(PHPBB_DATASET, PHPBB_SEED_FILE, PHPBB_CONFIG_FILE, PHPBB_RESULTS_FILE, false);
//Train on the toyDistribution dataset and evolve against the toyDistribution dataset
//RunExperiment(TOY_DISTRIBUTION_CONFIG_FILE, false);
// Print some summary statistics about the distribution of passwords in the two morphed english dictionaries.
// PasswordUtil.PrintStats(@"../../../passwords/morphed_english.txt"); // no creation rules
// PasswordUtil.PrintStats(@"../../../passwords/forced_morphed_english.txt"); // digit and length rules
// Run a really big analysis comparing the first-order Markov model to an 8-layered one.
// PrepareMarkovModelRuns();
// Parallel.For(0, _datasetFilenames.Length, i => RunAllMarkovModelPairs(i));
// Check if a database of hashed passwords contains some common passwords (check for creation rules)
// MD5HashChecker md5 = new MD5HashChecker(@"../../../passwords/stratfor_hashed.txt");
// md5.PrintCounts();
// Load the training set passwords from file
var passwords = PasswordUtil.LoadPasswords(@"/Users/Wesley/Projects/password-evolution/passwords/morphed_english.txt", 8);
// Create a Markov model from the passwords. This model will be used
// as our seed for the evolution.
int outputs = MarkovFilterCreator.GenerateFirstOrderMarkovFilter(
@"/Users/Wesley/Projects/password-evolution/models/supervised/morphed_english.xml", passwords);
Console.WriteLine("Outputs: {0}", outputs);
}
// Runs a comparison of the two model types.
static void RunAllMarkovModelPairs(object special)
{
const string EXPERIMENT_OFFSET = @"..\..\..\experiments\intermediate\";
string[] models = new string[]
{
"first-order",
"8-layer"
};
// For every dataset, create a model
for (int i = 0; i < _datasetFilenames.Length; i++)
{
if (i != (int)special)
{
continue;
}
for (int m = 0; m < 2; m++)
{
int outputs;
string seedFile = EXPERIMENT_OFFSET + "seed-" + models[m] + "-" + _datasetFilenames[i].Name + ".xml";
Console.Write("Building {0} Markov model...", models[m]);
if (m == 0)
{
outputs = MarkovFilterCreator.GenerateFirstOrderMarkovFilter(seedFile, _passwords[i]);
}
else
{
outputs = MarkovFilterCreator.GenerateLayeredMarkovFilter(seedFile, _passwords[i], 8);
}
Console.WriteLine("Done! Outputs: {0}", outputs);
_experiment.OutputCount = outputs;
Console.WriteLine("Loading seed...");
var seed = _experiment.LoadPopulation(XmlReader.Create(seedFile))[0];
Console.WriteLine("Creating model...");
var model = _experiment.CreateGenomeDecoder().Decode(seed);
// For every dataset, test the model
for (int j = 0; j < _datasetFilenames.Length; j++)
{
Console.Write("Validating {0} {1} model on {2} with {3} guesses... ", models[m], _datasetFilenames[i].Name, _datasetFilenames[j].Name, VALIDATION_GUESSES);
PasswordCrackingEvaluator eval = new PasswordCrackingEvaluator(VALIDATION_GUESSES, false);
var results = eval.Validate(model, _passwords[j], EXPERIMENT_OFFSET + models[m] + "-" + _datasetFilenames[i].Name + "-" + _datasetFilenames[j].Name + ".csv", 10000);
// Console.WriteLine("Accounts: {0} Uniques: {1}", results._fitness, results._alternativeFitness);
Console.WriteLine("Total Score: {0} Uniques: {1}", results._fitness, results._alternativeFitness);
lock (_writerLock)
using (TextWriter writer = new StreamWriter(@"..\..\..\experiments\summary_results.csv", true))
writer.WriteLine("{0},{1},{2},{3},{4}%,{5}%",
_datasetFilenames[i].Name,
_datasetFilenames[j].Name,
results._fitness,
results._alternativeFitness,
results._fitness / (double)_passwords[j].Sum(kv => kv.Value) * 100,
results._alternativeFitness / (double)_passwords[j].Count * 100);
}
}
}
}
/// <summary>
/// Trains a Markov model on a the training set of passwords, then evolves it against the target password database
/// specified in the config file. At the end of the evolution, the champion model is evaluated for a larger number
/// of guesses.
/// </summary>
/// <param name="trainingSetFile">The file containing the passwords from which to build the initial Markov model.</param>
/// <param name="seedFile">The file to which the initial Markov model will be saved.</param>
/// <param name="configFile">The file containing all the configuration parameters of the evolution.</param>
/// <param name="resultsFile">The file to which the results will be saved at each generation.</param>
/// <param name="validateSeed">If true, the seed model will first be validated against a large number of guesses.</param>
//private static void RunExperiment(string trainingSetFile, string seedFile, string configFile, string resultsFile, bool validateSeed = false)
private static void RunExperiment(string configFile, bool validateSeed = false)
{
Console.Write("Building Markov model...");
// Load the XML configuration file
XmlDocument xmlConfig = new XmlDocument();
xmlConfig.Load(configFile);
XmlElement xmlConfigElement = xmlConfig.DocumentElement;
// Set Training File
string trainingSetFile = XmlUtils.GetValueAsString(xmlConfigElement, "TrainingFile");
// Create seedFile
string seedFile = XmlUtils.GetValueAsString(xmlConfigElement, "SeedFile");
// Create results file.
string resultsFile = XmlUtils.GetValueAsString(xmlConfigElement, "ResultsFile");
Console.WriteLine("\nTraining File: {0}\nSeed File: {1}\nResults File: {2}", trainingSetFile, seedFile, resultsFile);
// Load the training set passwords from file
var passwords = PasswordUtil.LoadPasswords(trainingSetFile, 8);
// Create a Markov model from the passwords. This model will be used
// as our seed for the evolution.
int outputs = MarkovFilterCreator.GenerateFirstOrderMarkovFilter(seedFile, passwords);
// Free up the memory used by the passwords
passwords = null;
Console.WriteLine("Done! Outputs: {0}", outputs);
_experiment = new PasswordEvolutionExperiment();
_experiment.OutputCount = outputs;
// Initialize the experiment with the specifications in the config file.
_experiment.Initialize("PasswordEvolution", xmlConfig.DocumentElement);
// Set the passwords to be used by the fitness evaluator.
// These are the passwords our models will try to guess.
// PasswordsWithAccounts is the file used for validation. Its account values won't be changed.
PasswordCrackingEvaluator.Passwords = _experiment.Passwords;
PasswordCrackingEvaluator.PasswordsWithAccounts = new Dictionary <string, double>(_experiment.Passwords); // Makes a deep copy
Console.WriteLine("Loading seed...");
// Load the seed model that we created at the start of this function
var seed = _experiment.LoadPopulation(XmlReader.Create(seedFile))[0];
// Validates the seed model by running it for a large number of guesses
if (validateSeed)
{
Console.WriteLine("Validating seed model...");
var seedModel = _experiment.CreateGenomeDecoder().Decode(seed);
ValidateModel(seedModel, _experiment.Passwords, VALIDATION_GUESSES, _experiment.Hashed);
}
// Create evolution algorithm using the seed model to initialize the population
Console.WriteLine("Creating population...");
_ea = _experiment.CreateEvolutionAlgorithm(seed);
// Attach an update event handler. This will be called at the end of every generation
// to log the progress of the evolution (see function logEvolutionProgress below).
_ea.UpdateEvent += new EventHandler(logEvolutionProgress);
//_ea.UpdateScheme = new UpdateScheme(1);//.UpdateMode.
// Setup results file
using (TextWriter writer = new StreamWriter(resultsFile))
writer.WriteLine("Generation,Champion Accounts,Champion Uniques,Average Accounts,Average Uniques,Total Accounts,Total Uniques");
_generationalResultsFile = resultsFile;
// Start algorithm (it will run on a background thread).
Console.WriteLine("Starting evolution. Pop size: {0} Guesses: {1}", _experiment.DefaultPopulationSize, _experiment.GuessesPerIndividual);
_ea.StartContinue();
// Wait until the evolution is finished.
while (_ea.RunState == RunState.Running)
{
Thread.Sleep(1000);
}
// Validate the resulting model.
var decoder = _experiment.CreateGenomeDecoder();
var champ = decoder.Decode(_ea.CurrentChampGenome);
ValidateModel(champ, _experiment.Passwords, VALIDATION_GUESSES, _experiment.Hashed);
}
/// <summary>
/// Trains a Markov model on a the training set of passwords, then evolves it against the target password database
/// specified in the config file. At the end of the evolution, the champion model is evaluated for a larger number
/// of guesses.
/// </summary>
/// <param name="trainingSetFile">The file containing the passwords from which to build the initial Markov model.</param>
/// <param name="seedFile">The file to which the initial Markov model will be saved.</param>
/// <param name="configFile">The file containing all the configuration parameters of the evolution.</param>
/// <param name="resultsFile">The file to which the results will be saved at each generation.</param>
/// <param name="validateSeed">If true, the seed model will first be validated against a large number of guesses.</param>
//private static void RunExperiment(string trainingSetFile, string seedFile, string configFile, string resultsFile, bool validateSeed = false)
private static void RunExperiment(string configFile, bool validateSeed = false)
{
Console.WriteLine("Removing previous champions...");
string[] oldChampionFiles = Directory.GetFiles(@"../../../experiments/champions/", "*.xml");
foreach (string oldChampion in oldChampionFiles)
{
File.Delete(oldChampion);
}
Console.Write("Building Markov model...");
// Load the XML configuration file
XmlDocument xmlConfig = new XmlDocument();
xmlConfig.Load(configFile);
XmlElement xmlConfigElement = xmlConfig.DocumentElement;
// Set Training File
string trainingSetFile = XmlUtils.GetValueAsString(xmlConfigElement, "TrainingFile");
// Create seedFile
string seedFile = XmlUtils.GetValueAsString(xmlConfigElement, "SeedFile");
// Create results file.
string resultsFile = XmlUtils.GetValueAsString(xmlConfigElement, "ResultsFile");
Console.WriteLine();
Console.WriteLine("Training File: {0}", trainingSetFile);
Console.WriteLine("Seed File: {0}", seedFile);
Console.WriteLine("Results File: {0}", resultsFile);
// Load the training set passwords from file
var passwords = PasswordUtil.LoadPasswords(trainingSetFile, 8);
// Create a Markov model from the passwords. This model will be used
// as our seed for the evolution.
int outputs = MarkovFilterCreator.GenerateFirstOrderMarkovFilter(seedFile, passwords);
// Free up the memory used by the passwords
passwords = null;
Console.WriteLine("Done! Outputs: {0}", outputs);
_experiment = new PasswordEvolutionExperiment();
_experiment.OutputCount = outputs;
// Initialize the experiment with the specifications in the config file.
_experiment.Initialize("PasswordEvolution", xmlConfig.DocumentElement);
// Set the passwords to be used by the fitness evaluator.
// These are the passwords our models will try to guess.
// PasswordsWithAccounts is the file used for validation. Its account values won't be changed.
PasswordCrackingEvaluator.Passwords = _experiment.Passwords;
Console.WriteLine("Loading seed...");
// Load the seed model that we created at the start of this function
var seed = _experiment.LoadPopulation(XmlReader.Create(seedFile))[0];
// Validates the seed model by running it for a large number of guesses
if (validateSeed)
{
Console.WriteLine("Validating seed model...");
var seedModel = _experiment.CreateGenomeDecoder().Decode(seed);
ValidateModel(seedModel, _experiment.Passwords, VALIDATION_GUESSES, _experiment.Hashed);
}
// Create evolution algorithm using the seed model to initialize the population
Console.WriteLine("Creating population...");
_ea = _experiment.CreateEvolutionAlgorithm(seed);
// Attach an update event handler. This will be called at the end of every generation
// to log the progress of the evolution (see function logEvolutionProgress below).
_ea.UpdateEvent += new EventHandler(logEvolutionProgress);
//_ea.UpdateScheme = new UpdateScheme(1);//.UpdateMode.
// Setup results file
using (TextWriter writer = new StreamWriter(resultsFile))
writer.WriteLine("Generation,Champion Accounts,Champion Uniques,Average Accounts,Average Uniques,Total Accounts,Total Uniques");
_generationalResultsFile = resultsFile;
// Start algorithm (it will run on a background thread).
Console.WriteLine("Starting evolution. Pop size: {0} Guesses: {1}", _experiment.DefaultPopulationSize, _experiment.GuessesPerIndividual);
_ea.StartContinue();
// Wait until the evolution is finished.
while (_ea.RunState == RunState.Running)
{
Thread.Sleep(1000);
}
if (VALIDATE_ALL_STAR)
{
// Validate the champions of each generation.
List <MarkovChain> championModels = new List <MarkovChain>();
string[] championFiles = Directory.GetFiles(@"../../../experiments/champions/", "*.xml");
foreach (string championFile in championFiles)
{
var currentChamp = _experiment.LoadPopulation(XmlReader.Create(championFile))[0];
var champModel = _experiment.CreateGenomeDecoder().Decode(currentChamp);
championModels.Add(champModel);
}
ValidateForest(championModels, _experiment.Passwords, VALIDATION_GUESSES / championFiles.Length, _experiment.Hashed);
// Validate a population made up of copies of the final champion.
/* List<MarkovChain> championCopyPop = new List<MarkovChain>();
*
* Console.WriteLine();
* Console.WriteLine("Validating the final champion population");
* for (int i = 0; i < MAX_GENERATIONS; i++)
* {
* var decoder = _experiment.CreateGenomeDecoder();
* var champ = decoder.Decode(_ea.CurrentChampGenome);
* championCopyPop.Add(champ);
* }
* ValidateAllstarTeam(championCopyPop, _experiment.Passwords, VALIDATION_GUESSES, _experiment.Hashed);
*/
}
else
{
// Validate the resulting model.
var decoder = _experiment.CreateGenomeDecoder();
var champ = decoder.Decode(_ea.CurrentChampGenome);
ValidateModel(champ, _experiment.Passwords, VALIDATION_GUESSES, _experiment.Hashed);
}
}
