Carlos Gussenhoven

24 papers A 5Journal 10Unranked 9
YearRankTypeTitle / Venue / Authors
2025 J jnl
J. Phonetics
Lei Wang, Marco van de Ven, Carlos Gussenhoven
2023 J jnl
Phonetica
Man-ni Chu, Carlos Gussenhoven, Roeland van Hout
2022 J jnl
J. Phonetics
Judith Hanssen, Jörg Peters, Carlos Gussenhoven
2020 A conf
INTERSPEECH
Na Hu, Berit Janssen, Judith Hanssen, Carlos Gussenhoven, Aoju Chen
2016 J jnl
Top. Cogn. Sci.
Carlos Gussenhoven
2014 J jnl
J. Phonetics
Jörg Peters, Judith Hanssen, Carlos Gussenhoven
2013 A conf
INTERSPEECH
Carlos Gussenhoven, Wencui Zhou
2011 conf
ICPhS
Vahideh Abolhasani Zadeh, Carlos Gussenhoven, Mahmood Bijankhan
2011 J jnl
J. Phonetics
Marco van de Ven, Carlos Gussenhoven
2011 conf
ICPhS
Xuliang He, Judith Hanssen, Vincent J. van Heuven, Carlos Gussenhoven
2011 conf
ICPhS
Carlos Gussenhoven
2011 conf
ICPhS
Marinda Hagen, Joop Kerkhoff, Carlos Gussenhoven
2008 J jnl
J. Phonetics
Yiya Chen, Carlos Gussenhoven
2008 conf
ExLing
Man-ni Chu, Carlos Gussenhoven, Roeland van Hout
2007 A conf
INTERSPEECH
Jörg Peters, Judith Hanssen, Carlos Gussenhoven
2006 J jnl
J. Phonetics
Rachel Fournier, Jo Verhoeven, Marc Swerts, Carlos Gussenhoven
2004 J jnl
J. Phonetics
Toni C. M. Rietveld, Joop Kerkhoff, Carlos Gussenhoven
2002 J jnl
Phonetica
Toni C. M. Rietveld, Judith Haan, Linda Heijmans, Carlos Gussenhoven
2001 A conf
INTERSPEECH
Aoju Chen, Toni C. M. Rietveld, Carlos Gussenhoven
2000 A conf
INTERSPEECH
Carlos Gussenhoven, Aoju Chen
1997 conf
EUROSPEECH
Toni C. M. Rietveld, Carlos Gussenhoven
1994 conf
ICSLP
Carlos Gussenhoven, Toni C. M. Rietveld
1994 conf
SSW
Erwin Marsi, Peter-Arno Coppen, Carlos Gussenhoven, Toni C. M. Rietveld
1992 conf
ICSLP
Carlos Gussenhoven, Toni C. M. Rietveld
redb/extractors/pe_extractors/pe_overlay.py
← Index redb/extractors/pe_extractors/pe_overlay.py python
from hashlib import md5, sha1, sha256
import inspect
from datetime import datetime, timezone
from typing import Any

import magic
from magika import Magika

from redb.extractors.enum import Tag
from redb.extractors.pe_extractor import PEExtractor
from redb.models.dataclasses import PEOverlay


class PEOverlayExtractor(PEExtractor):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        elastic_index=None,
        known_benign=False,
        known_malicious=False,
        pe=None,
    ):
        super().__init__(
            filepath,
            log,
            exporters,
            index_prefix,
            elastic_index,
            known_benign,
            known_malicious,
            pe,
        )
        self.elastic_index = self.index_prefix + "-pe_overlay"
        self.log.debug(inspect.currentframe().f_code.co_name)

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

    def _extract_pe_overlay(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        overlay = self.pe.get_overlay()
        if overlay:
            return PEOverlay(
                _id=sha256(overlay).hexdigest(),
                overlay_size=len(overlay),
                overlay_entropy=self.calculate_entropy(overlay),
                overlay_offset=self.pe.get_overlay_data_start_offset(),
                overlay_mimetype=magic.from_buffer(overlay, mime=True),
                overlay_type=magic.from_buffer(overlay),
                overlay_magika=Magika().identify_bytes(overlay).output.ct_label,
                overlay_sha256=sha256(overlay).hexdigest(),
                overlay_sha1=sha1(overlay).hexdigest(),
                overlay_md5=md5(overlay).hexdigest(),
            )
        return None

    def extract(self):
        try:
            self.log.debug(inspect.currentframe().f_code.co_name)
            overlay = self._extract_pe_overlay()
            # self.export_to_elastic([overlay])  # Let the exporters handle this
            return overlay
        except Exception as e:
            self.log.error(f"Error extracting PE overlay: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.extract()
        elif exporter_type == "ClickHouseExporter":
            overlay = self.extract()
            if overlay is None:
                return None
            
            data = []
            current_time = datetime.now(timezone.utc)
            
            data.append([
                self.sha256,              # sha256
                self.md5,                 # md5
                self.sha1,                # sha1
                overlay.overlay_size,     # overlay_size
                overlay.overlay_entropy,  # overlay_entropy
                overlay.overlay_offset,   # overlay_offset
                overlay.overlay_mimetype, # overlay_mimetype
                overlay.overlay_type,     # overlay_type
                overlay.overlay_magika,   # overlay_magika
                overlay.overlay_sha256,   # overlay_sha256
                overlay.overlay_sha1,     # overlay_sha1
                overlay.overlay_md5,      # overlay_md5
                current_time             # analysis_date
            ])
            
            column_names = [
                'sha256', 'md5', 'sha1', 'overlay_size', 'overlay_entropy',
                'overlay_offset', 'overlay_mimetype', 'overlay_type', 'overlay_magika',
                'overlay_sha256', 'overlay_sha1', 'overlay_md5',
                'analysis_date'
            ]
            
            if not data:
                return None

            column_type_names = [
                'FixedString(64)', 'FixedString(32)', 'FixedString(40)',
                'UInt64', 'Float64', 'UInt64',
                'LowCardinality(String)', 'LowCardinality(String)', 'LowCardinality(String)',
                'FixedString(64)', 'FixedString(40)', 'FixedString(32)',
                'DateTime64(3, \'UTC\')'
            ]

            return (data, column_names, column_type_names)

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