Maja Pusnik

39 papers C 9Journal 12Unranked 18
YearRankTypeTitle / Venue / Authors
2025 conf
exp.at
Olga Dziabenko, Diego López-de-Ipiña, Javier García-Zubía, Unai Hernández-Jayo, Maja Pusnik, Bostjan Sumak, Sérgio Duarte Correia, Tuncer Can, Darja Ivanusa Kline
2024 conf
MIPRO
Bostjan Sumak, Diego López-de-Ipiña, Olga Dziabenko, Sérgio Duarte Correia, Luísa M. Serrano de Carvalho, Secundino Lopes, Irfan Simsek, Tuncer Can, Darja Ivanusa Kline, Maja Pusnik
2024 conf
MIPRO
Bostjan Sumak, Sérgio Duarte Correia, Ana Cunha, Tuncer Can, Irfan Simsek, Katja Kous, Maja Pusnik
2023 C conf
EJC
Maja Pusnik, Katja Kous, Tatjana Welzer-Druzovec, Bostjan Sumak
2022 C conf
EJC
Bostjan Sumak, Maja Pusnik
2022 conf
SQAMIA
Filip Pasaric, Maja Pusnik
2022 J jnl
Sensors
Bostjan Sumak, Sasa Brdnik, Maja Pusnik
2021 J jnl
Univers. Access Inf. Soc.
Katja Kous, Sasa Kuhar, Miha Pavlinek, Marjan Hericko, Maja Pusnik
2020 C conf
EJC
Yukiko Sato, Stefan Brückner, Maja Pusnik
2020 C conf
EJC
Bostjan Sumak, Marjan Hericko, Maja Pusnik
2020 J jnl
Sensors
Maja Pusnik, Mitja Galun, Bostjan Sumak
2020 J jnl
J. Libr. Inf. Sci.
Katja Kous, Maja Pusnik, Marjan Hericko, Gregor Polancic
2019 C conf
EJC
Gregor Polancic, Bostjan Sumak, Maja Pusnik
2019 C conf
EJC
Maja Pusnik, Tatjana Welzer-Druzovec, Marjan Hericko, Bostjan Sumak
2019 J jnl
J. Biomed. Informatics
Bostjan Sumak, Matic Spindler, Mojca Debeljak, Marjan Hericko, Maja Pusnik
2019 conf
MIPRO
Katja Kous, Sasa Kuhar, Maja Pusnik, Bostjan Sumak
2019 conf
SQAMIA
Maja Pusnik, Katja Kous, Andrej Godec, Bostjan Sumak
2018 C conf
EJC
Maja Pusnik, Dimitar Ivanovski, Tatjana Welzer-Druzovec, Bostjan Sumak
2018 conf
SQAMIA
Maja Pusnik, Bostjan Sumak, Marjan Hericko, Gordana Rakic, Zoran Budimac
2017 conf
SQAMIA
David Kostanjevec, Maja Pusnik, Marjan Hericko, Bostjan Sumak, Gordana Rakic, Zoran Budimac
2017 conf
MIPRO
Bostjan Sumak, Matic Spindler, Maja Pusnik
2017 J jnl
Comput. Hum. Behav.
Bostjan Sumak, Maja Pusnik, Marjan Hericko, Andrej Sorgo
2017 J jnl
Comput. Sci. Inf. Syst.
Bostjan Sumak, Marjan Hericko, Zoran Budimac, Maja Pusnik
2017 conf
MIPRO
Maja Pusnik, Dimitar Ivanovski, Bostjan Sumak
2016 C conf
EJC
Bostjan Sumak, Marjan Hericko, Tatjana Welzer-Druzovec, Maja Pusnik
2016 conf
SQAMIA
Maja Pusnik, Marjan Hericko, Bostjan Sumak, Gordana Rakic
2015 C conf
EJC
Maja Pusnik, Marjan Hericko, Bostjan Sumak
2015 conf
KMO
Bostjan Sumak, Matej Stumpfl, Maja Pusnik
2014 conf
MIPRO
Bostjan Sumak, Maja Pusnik, Marjan Hericko
2014 J jnl
Int. J. Softw. Eng. Knowl. Eng.
Maja Pusnik, Katja Harej Pulko, Marjan Hericko, Matjaz B. Juric, Bostjan Sumak
2014 conf
MIPRO
Maja Pusnik, Marjan Hericko, Bostjan Sumak
2014 J jnl
Comput. Sci. Inf. Syst.
Maja Pusnik, Marjan Hericko, Zoran Budimac, Bostjan Sumak
2013 conf
SQAMIA
Maja Pusnik, Bostjan Sumak, Zoran Budimac, Marjan Hericko
2012 conf
ITI
Bostjan Sumak, Maja Pusnik, Marjan Hericko
2012 conf
ITI
Maja Pusnik, Bostjan Sumak, Marjan Hericko
2011 J jnl
Comput. Hum. Behav.
Bostjan Sumak, Marjan Hericko, Maja Pusnik
2011 J jnl
Informatica (Slovenia)
Bostjan Sumak, Marjan Hericko, Maja Pusnik, Gregor Polancic
2003 conf
Bled eConference
Matjaz B. Juric, Maja Pusnik, Ivan Rozman, Boltjan Lumak
2002 J jnl
Informatica (Slovenia)
Maja Pusnik, Matjaz B. Juric, Ivan Rozman
redb/extractors/basicproperties.py
← Index redb/extractors/basicproperties.py python
from dataclasses import asdict
import inspect
import os
import magic
from magika import Magika
from datetime import datetime, timezone
from typing import Any, List, Tuple

from redb.extractors.enum import Tag
from redb.models.dataclasses import BasicProperties
from redb.extractors.extractor import Extractor


class BasicPropertiesExtractor(Extractor):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        elastic_index=None,
        known_benign=False,
        known_malicious=False,
        parent_sha256=None,
        precomputed_hashes=None,
        is_fat=None,
        child_sha256=None,
        child_architecture=None,
        child_filetype=None,
        first_seen=None,
    ):
        super().__init__(
            filepath,
            log,
            exporters=exporters,
            index_prefix=index_prefix,
            elastic_index=elastic_index,
            known_benign=known_benign,
            known_malicious=known_malicious,
            precomputed_hashes=precomputed_hashes,
        )
        self.basic_properties = None
        self.elastic_index = self.index_prefix + "-basic_properties"
        self.is_packed = None
        self.parent_sha256 = parent_sha256  # For FAT Mach-O slices, points to container hash
        self.is_fat = is_fat  # True for FAT Mach-O containers, None otherwise
        self.child_sha256 = child_sha256  # SHA256 hashes of children (FAT slices, zip contents)
        self.child_architecture = child_architecture  # Architecture names for FAT Mach-O slices
        self.child_filetype = child_filetype  # Magika filetypes for children (useful for zip archives)
        self.first_seen = first_seen  # From catalog_samples, None for local files

    def tag(self):
        return Tag.BASIC_PROPERTIES.value

    def _extract_basic_properties(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        filename = None  # Reserved for future use
        sample_name = os.path.basename(self.filepath)
        file_entropy = round(self.calculate_entropy(self.binary), 3)
        type_ = magic.from_buffer(self.binary)
        type_mime = magic.from_buffer(self.binary, mime=True)
        type_magika = Magika().identify_bytes(self.binary).output.label
        size = len(self.binary)
        self.basic_properties = BasicProperties(
            filename, sample_name, size, type_, type_mime, type_magika,
            file_entropy, self.is_packed, self.is_fat, self.child_sha256,
            self.child_architecture, self.child_filetype,
            first_seen=str(self.first_seen) if self.first_seen else None,
        )
        self.log.debug(f"Basic Properties dump: {asdict(self.basic_properties)}")

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            self._extract_basic_properties()
            # self.export_to_elastic([self.basic_properties])
            return self.basic_properties
        except Exception as e:
            self.log.error(f"Extract basic properties error {self.hash.sha256} Exception: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.basic_properties
        elif exporter_type == "ClickHouseExporter":
            data = [[
                self.sha256,
                self.md5,
                self.sha1,
                self.parent_sha256,  # NULL for standalone/FAT, fat_hash for slices
                self.basic_properties.child_sha256 or [],  # SHA256 hashes of children
                self.basic_properties.child_architecture or [],  # Architecture names for FAT slices
                self.basic_properties.child_filetype or [],  # Magika filetypes for children
                self.basic_properties.is_fat,  # True for FAT Mach-O containers, NULL otherwise
                self.basic_properties.filename,
                self.basic_properties.sample_name,
                self.basic_properties.filesize,
                self.basic_properties.file_entropy,
                self.basic_properties.filetype,
                self.basic_properties.filetype_mime,
                self.basic_properties.filetype_magika,
                self.first_seen or datetime(1970, 1, 1, tzinfo=timezone.utc),  # From catalog_samples, epoch zero for local files (uses original datetime, not string)
                datetime.now(timezone.utc)
            ]]

            column_names = [
                'sha256', 'md5', 'sha1', 'parent_sha256', 'child_sha256', 'child_architecture', 'child_filetype',
                'is_fat', 'filename', 'sample_name',
                'filesize', 'file_entropy', 'filetype', 'filetype_mime',
                'filetype_magika', 'first_seen', 'analysis_date'
            ]

            column_type_names = [
                'String', 'String', 'String', 'Nullable(String)',
                'Array(FixedString(64))', 'Array(LowCardinality(String))', 'Array(LowCardinality(String))',
                'Nullable(UInt8)', 'Nullable(String)', 'String',
                'UInt64', 'Float64', 'LowCardinality(String)',
                'LowCardinality(String)', 'LowCardinality(String)',
                'DateTime64(3, \'UTC\')',
                'DateTime64(3, \'UTC\')'
            ]

            return data, column_names, column_type_names

    def get_clickhouse_table(self) -> str:
        return "redb_basic_properties"