malwareDetector 0.1.0__py3-none-any.whl

malwareDetector/__init__.py

@@ -0,0 +1,10 @@
+# -*- coding: utf-8 -*-
+
+"""detector
+
+This is a malware detector spec for NTUST isLab.
+"""
+
+from importlib.metadata import version
+
+__version__ = version(__package__)

malwareDetector/config.py

@@ -0,0 +1,220 @@
+"""Load all user defined config and env vars."""
+
+import logging
+import os
+import argparse
+from pydantic import BaseModel
+from .const import *
+
+class PathConfig(BaseModel):
+    input: str = DEFAULT_INPUT_PATH
+    output: str = DEFAULT_OUT_PATH
+
+class ModelConfig(BaseModel):
+    modelName: str = DEFAULT_MODEL_NAME
+    dimensions: int = DEFAULT_DIMENSIONS
+    workers: int = DEFAULT_WORKERS
+    epochs: int = DEFAULT_EPOCHS
+    min_count: int = DEFAULT_MIN_COUNT
+    wl_iterations: int = DEFAULT_WL_ITERATIONS
+    learning_rate: float = DEFAULT_LEARNING_RATE
+    down_sampling: float = DEFAULT_DOWN_SAMPLING
+    judge: int = DEFAULT_JUDGE
+
+class FolderConfig(BaseModel):
+    dataset:str = DATASET_DIR
+    feature:str = FEATURE_DIR
+    vectorize:str = VECTORIZE_DIR
+    model:str = MODEL_DIR
+    predict:str = PREDICT_DIR
+
+    def __iter__(self):
+        folder_list = [DATASET_DIR, FEATURE_DIR, VECTORIZE_DIR, MODEL_DIR, PREDICT_DIR]
+        return FolderClassIter(folder_list)
+
+class FolderClassIter(object):
+    def __init__(self, folder_list):
+        self._folder = folder_list
+        self._folder_size = len(folder_list)
+        self._current_index = 0
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        if self._current_index < self._folder_size:
+            member = self._folder[self._current_index]
+            self._current_index += 1
+            return member
+        raise StopIteration
+
+class Config(BaseModel):
+    """The blueprint for detector's whole config."""
+
+    # pylint: disable=too-few-public-
+    path: PathConfig = PathConfig()
+    folder: FolderConfig = FolderConfig()
+    model: ModelConfig = ModelConfig()
+    classify: bool = DEFAULT_CLASSIFY
+
+def parameter_parser(config: Config) -> Config:
+        """
+        A method to parse up command line parameters.
+        By default it gives an embedding of the partial NCI1 graph dataset.
+        The default hyperparameters give a good quality representation without grid search.
+        Representations are sorted by ID.
+        """
+        parser = argparse.ArgumentParser(description="Run Graph2Vec.")
+
+        parser.add_argument("--input-path","-i",
+                            dest="input_path",
+                            nargs="?",
+                            default=DEFAULT_INPUT_PATH,
+                            help="Input folder with jsons."
+                            )
+
+        parser.add_argument("--output-path","-o",
+                            dest="output_path",
+                            nargs="?",
+                            default=DEFAULT_OUT_PATH,
+                            help="Embeddings path."
+                            )
+
+        parser.add_argument("--dimensions",
+                            dest="dimensions",
+                            type=int,
+                            default=DEFAULT_DIMENSIONS,
+                            help="Number of dimensions. Default is 128."
+                            )
+
+        parser.add_argument("--workers",
+                            dest="workers",
+                            type=int,
+                            default=DEFAULT_WORKERS,
+                            help="Number of workers. Default is 4."
+                            )
+
+        parser.add_argument("--epochs",
+                            dest="epochs",
+                            type=int,
+                            default=DEFAULT_EPOCHS,
+                            help="Number of epochs. Default is 10."
+                            )
+
+        parser.add_argument("--min-count",
+                            dest="min_count",
+                            type=int,
+                            default=DEFAULT_MIN_COUNT,
+                            help="Minimal structural feature count. Default is 5."
+                            )
+
+        parser.add_argument("--wl-iterations",
+                            dest="wl_iterations",
+                            type=int,
+                            default=DEFAULT_WL_ITERATIONS,
+                            help="Number of Weisfeiler-Lehman iterations. Default is 2."
+                            )
+
+        parser.add_argument("--learning-rate",
+                            dest="learning_rate",
+                            type=float,
+                            default=DEFAULT_LEARNING_RATE,
+                            help="Initial learning rate. Default is 0.025."
+                            )
+
+        parser.add_argument("--down-sampling",
+                            dest="down_sampling",
+                            type=float,
+                            default=DEFAULT_DOWN_SAMPLING,
+                            help="Down sampling rate of features. Default is 0.0001."
+                            )
+
+        parser.add_argument("--judge",
+                            dest="judge",
+                            type=int,
+                            default=DEFAULT_JUDGE,
+                            help="Rename?"
+                            )
+
+        parser.add_argument('--model','-m',
+                            dest="model",
+                            nargs='?',
+                            default=DEFAULT_MODEL_NAME,
+                            help='Select the model(KNN,LR,MLP,RF,SVM).'
+                            )
+
+        parser.add_argument('--classify', '-c',
+                            dest="classify",
+                            action='store_true',
+                            help='apply the family classifier'
+                            )
+        args = parser.parse_args()
+        if hasattr(args, 'input_path'):
+            config.path.input = args.input_path
+        if hasattr(args, 'output_path'):
+            config.path.output = args.output_path
+        if hasattr(args, 'dimensions'):
+            config.model.dimensions = args.dimensions
+        if hasattr(args, 'workers'):
+            config.model.workers = args.workers
+        if hasattr(args, 'epochs'):
+            config.model.epochs = args.epochs
+        if hasattr(args, 'min_count'):
+            config.model.min_count = args.min_count
+        if hasattr(args, 'wl_iterations'):
+            config.model.wl_iterations = args.wl_iterations
+        if hasattr(args, 'learning_rate'):
+            config.model.learning_rate = args.learning_rate
+        if hasattr(args, 'down_sampling'):
+            config.model.down_sampling = args.down_sampling
+        if hasattr(args, 'judge'):
+            config.model.judge = args.judge
+        if hasattr(args, 'model'):
+            config.model.modelName = args.model
+        if hasattr(args, 'classify'):
+            config.classify = args.classify
+
+        # return parser.parse_args()
+        return config
+
+def write_config_to_file(config: Config):
+    with open(CONFIG_FILE_NAME, "w", encoding="utf8") as file:
+        file.write(config.json())
+
+def detect_config_file(argparse: bool=False) -> None:
+    if argparse:
+        logging.info(
+            "Creating local config file by argparse."
+        )
+        write_config_to_file(parameter_parser(Config()))
+        logging.info(f"{CONFIG_FILE_NAME} created!")
+    elif CONFIG_FILE_NAME in os.listdir():
+        logging.info(f"{CONFIG_FILE_NAME} detected!")
+    else:
+        logging.info(
+            "config file not found. creating local config file by default config."
+        )
+        write_config_to_file(Config())
+        logging.info(f"{CONFIG_FILE_NAME} created!")
+
+def read_config(count=1) -> Config:
+    """Load the configuration defined by user."""
+    if count > 3:
+        logging.warning("Failed to read config, returning default config")
+        return Config()
+    if count != 1:
+        logging.info(f"Trying to read config time:{count}")
+    try:
+        with open(CONFIG_FILE_NAME, encoding="utf8") as file:
+            return Config.parse_raw(file.read())
+        # else:
+        #     return Config()
+    except Exception as err:
+        logging.warning(err)
+        detect_config_file(argparse=False)
+        return read_config(count=count+1)
+
+detect_config_file(argparse=True)
+CONFIG = read_config()
+
+logging.info("config.py got executed")

malwareDetector/const.py

@@ -0,0 +1,20 @@
+CONFIG_FILE_NAME="config.json"
+
+DEFAULT_INPUT_PATH="./Dataset/0481b823f05900ab9e4ac43d38bee84a912fa41f5796ce6ca820e259bc99cc63"
+DEFAULT_OUT_PATH="./Feature/nci1.csv"
+DEFAULT_MODEL_NAME="SVM"
+DEFAULT_DIMENSIONS=128
+DEFAULT_WORKERS=4
+DEFAULT_EPOCHS=50
+DEFAULT_MIN_COUNT=1
+DEFAULT_WL_ITERATIONS=2
+DEFAULT_LEARNING_RATE=0.025
+DEFAULT_DOWN_SAMPLING=0.0001
+DEFAULT_JUDGE=0
+DEFAULT_CLASSIFY=True
+
+DATASET_DIR="./Dataset/"
+FEATURE_DIR="./Feature/"
+VECTORIZE_DIR="./Vectorize/"
+MODEL_DIR="./Model/"
+PREDICT_DIR="./Predict/"

malwareDetector/detector.py

@@ -0,0 +1,28 @@
+import os
+import numpy as np
+from .utils import platform_info
+from .config import CONFIG
+
+class detector(object):
+    def __init__(self) -> None:
+        self.config = CONFIG
+
+    def extractFeature(self) -> list:
+        raise NotImplementedError("extractFeature must be implemented in the derived class.")
+
+    def vectorize(self) -> np.array:
+        raise NotImplementedError("vectorize must be implemented in the derived class.")
+
+    def model(self):
+        raise NotImplementedError("model must be implemented in the derived class.")
+
+    def predict(self):
+        raise NotImplementedError("predict must be implemented in the derived class.")
+
+    def mkdir(self, folder_list) -> None:
+        for folder in folder_list:
+            if not os.path.exists(folder):
+                os.mkdir(folder)
+
+if __name__ == "__main__":
+    platform_info()

malwareDetector/utils.py

@@ -0,0 +1,10 @@
+from . import __version__
+import sys, os, platform
+
+def platform_info():
+    nl = "\n"
+    return f"""Running tgcf {__version__}\
+    \nPython {sys.version.replace(nl,"")}\
+    \nOS {os.name}\
+    \nPlatform {platform.system()} {platform.release()}\
+    \n{platform.architecture()} {platform.processor()}"""

malwareDetector-0.1.0.dist-info/LICENCE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 (PO-LIN LAI)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

malwareDetector-0.1.0.dist-info/METADATA

@@ -0,0 +1,55 @@
+Metadata-Version: 2.1
+Name: malwareDetector
+Version: 0.1.0
+Summary: Malware detector specification for NTUST isLab
+Author: PO-LIN LAI
+Author-email: bolin8017@gmail.com
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENCE.txt
+Requires-Dist: numpy
+Requires-Dist: pydantic
+
+malwareDetector
+===================
+
+[GitHub](https://github.com/louiskyee/malwareDetector.git)
+
+Description
+-----------
+
+This is a malware detector specification for NTUST isLab.
+
+Installation
+------------
+
+Use the package manager [pip](https://pip.pypa.io/en/stable/) to install `malwareDetector`.
+
+Usage
+-----
+
+### import
+* import class `detector` from `malwareDetector.detector`
+```python=
+from malwareDetector.detector import detector
+```
+
+### Examples:
+```python=
+from malwareDetector.detector import detector
+import numpy as np
+
+class subDetector(detector):
+    def extractFeature(self) -> list:
+        return 'This is the implementation of the extractFeature function from the derived class.'
+
+    def vectorize(self) -> np.array:
+        return 'This is the implementation of the vectorize function from the derived class.'
+
+    def model(self):
+        return 'This is the implementation of the model function from the derived class.'
+
+    def predict(self):
+        return 'This is the implementation of the predict function from the derived class.'
+```

malwareDetector-0.1.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+malwareDetector/__init__.py,sha256=KlbADAUEmORAxlQoZ9JeppK6dZplWNgJfz_noesWwH0,175
+malwareDetector/config.py,sha256=ZqfO4T07_S5x6oZwWhr_QI4zuA7Y7BdshkCGCbg6nlc,8299
+malwareDetector/const.py,sha256=DmVapJFZsmrK65UFjJdNaPnjIhf7cuqrawXzxmeoO6E,533
+malwareDetector/detector.py,sha256=GNuDVXbdNizEYRYsBIDSfE2C4AlL6A7nNy1JuasK_oA,881
+malwareDetector/utils.py,sha256=RhE8BuDKT7lRT69jzvRlzDHF-YfnIGN1P4tieXCVwoI,307
+malwareDetector-0.1.0.dist-info/LICENCE.txt,sha256=2XPCaZqZ-jgHh7e1DKa87JUeuOB6DC0jaZonmjDeILM,1088
+malwareDetector-0.1.0.dist-info/METADATA,sha256=T5ud1YcPfN6UHPa8rmD9vB5DYkCUhpix30ejhb7i3I4,1438
+malwareDetector-0.1.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+malwareDetector-0.1.0.dist-info/top_level.txt,sha256=wRXSanQD5XDXRYp3lPh1SjltOo6rpC5jktmR69tqIQo,16
+malwareDetector-0.1.0.dist-info/RECORD,,

malwareDetector-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.38.4)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

malwareDetector-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+malwareDetector