Nixyri/ghidra
1
0
Fork 0
mirror of https://github.com/NationalSecurityAgency/ghidra.git synced 2024-11-22 12:11:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

GP-1 script cleanup

Browse Source
This commit is contained in:
ghidra1 2022-10-21 13:02:33 -04:00
parent 2a2b044940
commit 43675121b0
3 changed files with 0 additions and 179 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
Ghidra/Extensions/MachineLearning/developer_scripts/DumpCalls.java
View File

@ -1,58 +0,0 @@
/* ###
* IP: GHIDRA
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
//Writes a list of the addresses of all call sites to a file.
//@category machineLearning
import java.io.*;
import ghidra.app.script.GhidraScript;
import ghidra.program.model.listing.*;
import ghidra.program.model.pcode.PcodeOp;
public class DumpCalls extends GhidraScript {
private static final String DATA_DIR = "/local/calls";
@Override
protected void run() throws Exception {
File outFile = new File(DATA_DIR + File.separator + currentProgram.getName() + "_calls");
FileWriter fWriter = new FileWriter(outFile);
BufferedWriter bWriter = new BufferedWriter(fWriter);
InstructionIterator fIter = currentProgram.getListing().getInstructions(true);
int numCalls = 0;
int numInstructions = 0;
while (fIter.hasNext()) {
Instruction inst = fIter.next();
if (inst.getPcode() == null || inst.getPcode().length == 0) {
continue;
}
numInstructions++;
for (int i = 0; i < inst.getPcode().length; i++) {
PcodeOp pCode = inst.getPcode()[i];
int opCode = pCode.getOpcode();
if (opCode == PcodeOp.CALL || opCode == PcodeOp.CALLIND) {
//printf("Inst: %s at %s\n", inst.toString(), inst.getAddress());
numCalls++;
bWriter.write(inst.getAddress().toString() + "\n");
}
}
}
printf("total num calls: %d\n", numCalls);
printf("total num instructions: %d\n", numInstructions);
bWriter.close();
}
}

47
Ghidra/Extensions/MachineLearning/developer_scripts/DumpFunctionStarts.java
View File

@ -1,47 +0,0 @@
/* ###
* IP: GHIDRA
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
//Writes a list of the addresses of all function starts and their sizes to a file
//@category machineLearning
import java.io.*;
import ghidra.app.script.GhidraScript;
import ghidra.program.model.listing.Function;
import ghidra.program.model.listing.FunctionIterator;
public class DumpFunctionStarts extends GhidraScript {
private static final String DATA_DIR = "/local/funcstarts/stripped";
@Override
protected void run() throws Exception {
File outFile =
new File(DATA_DIR + File.separator + currentProgram.getName() + "_stripped_funcs");
FileWriter fWriter = new FileWriter(outFile);
BufferedWriter bWriter = new BufferedWriter(fWriter);
FunctionIterator fIter = currentProgram.getFunctionManager().getFunctions(true);
while (fIter.hasNext()) {
Function func = fIter.next();
if (func.isExternal()) {
continue;
}
long size = func.getBody().getNumAddresses();
bWriter.write(func.getEntryPoint().toString() + "," + size + "\n");
}
bWriter.close();
}
}

74
Ghidra/Extensions/MachineLearning/developer_scripts/ExampleTribuoRunner.java
View File

@ -1,74 +0,0 @@
/* ###
* IP: GHIDRA
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.IOException;
import java.nio.file.Paths;
import org.tribuo.*;
import org.tribuo.classification.Label;
import org.tribuo.classification.LabelFactory;
import org.tribuo.classification.dtree.CARTClassificationTrainer;
import org.tribuo.classification.ensemble.VotingCombiner;
import org.tribuo.classification.evaluation.LabelEvaluation;
import org.tribuo.classification.evaluation.LabelEvaluator;
import org.tribuo.common.tree.RandomForestTrainer;
import org.tribuo.data.csv.CSVLoader;
import org.tribuo.ensemble.EnsembleModel;
import org.tribuo.evaluation.TrainTestSplitter;
public class ExampleTribuoRunner {
public static void main(String args[]) throws IOException {
var irisHeaders =
new String[] { "sepalLength", "sepalWidth", "petalLength", "petalWidth", "species" };
DataSource<Label> irisData = new CSVLoader<>(new LabelFactory()).loadDataSource(
Paths.get("/home/jmworth/ml/bezdekIris.data"), /* Output column */ irisHeaders[4],
/* Column headers */ irisHeaders);
// Split iris data into training set (70%) and test set (30%)
var splitIrisData =
new TrainTestSplitter<>(irisData, /* Train fraction */ 0.7, /* RNG seed */ 1L);
var trainData = new MutableDataset<>(splitIrisData.getTrain());
var testData = new MutableDataset<>(splitIrisData.getTest());
// We can train a decision tree
var cartTrainer = new CARTClassificationTrainer(100, (float) 0.2, 0);
var decisionTree = cartTrainer.train(trainData);
//Model<Label> tree = cartTrainer.train(trainData);
var trainer = new RandomForestTrainer<>(cartTrainer, // trainer - the tree trainer
new VotingCombiner(), // combiner - the combining function for the ensemble
10 // numMembers - the number of ensemble members to train
);
EnsembleModel<Label> tree = trainer.train(trainData);
// Finally we make predictions on unseen data
// Each prediction is a map from the output names (i.e. the labels) to the scores/probabilities
Prediction<Label> prediction = tree.predict(testData.getExample(0));
// Or we can evaluate the full test dataset, calculating the accuracy, F1 etc.
LabelEvaluation evaluation = new LabelEvaluator().evaluate(tree, testData);
// we can inspect the evaluation manually
double acc = evaluation.accuracy();
// which returns 0.978
// or print a formatted evaluation string
System.out.println(evaluation.toString());
}
}