Malte Nuhn

12 papers A* 2B 1Unranked 8
YearRankTypeTitle / Venue / Authors
2019
Malte Nuhn
2015 conf
ACL (2)
Malte Nuhn, Julian Schamper, Hermann Ney
2014 A* conf
EMNLP
Malte Nuhn, Kevin Knight
2014 conf
ACL (2)
Malte Nuhn, Hermann Ney
2014 A* conf
EMNLP
Malte Nuhn, Julian Schamper, Hermann Ney
2014 B conf
ICFHR
Michal Kozielski, Malte Nuhn, Patrick Doetsch, Hermann Ney
2013 conf
ACL (1)
Malte Nuhn, Julian Schamper, Hermann Ney
2013 conf
ACL (1)
Malte Nuhn, Hermann Ney
2012 conf
ACL (1)
Malte Nuhn, Arne Mauser, Hermann Ney
2012 conf
COLING (Demos)
Joern Wuebker, Matthias Huck, Stephan Peitz, Malte Nuhn, Markus Freitag, Jan-Thorsten Peter, Saab Mansour, Hermann Ney
2012 conf
WMT@NAACL-HLT
Matthias Huck, Stephan Peitz, Markus Freitag, Malte Nuhn, Hermann Ney
2012 conf
IWSLT
Stephan Peitz, Saab Mansour, Markus Freitag, Minwei Feng, Matthias Huck, Joern Wuebker, Malte Nuhn, Markus Nußbaum-Thom, Hermann Ney
redb/extractors/pe_extractors/pe_sections.py
← Index redb/extractors/pe_extractors/pe_sections.py python
import base64
import hashlib
import inspect
from redb.extractors.enum import Tag
from redb.extractors.pe_extractor import PEExtractor
from redb.models.dataclasses import PESection
from datetime import datetime, timezone
from typing import Any


class PESectionExtractor(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_sections"
        self.log.debug(inspect.currentframe().f_code.co_name)

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

    def _extract_sections(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        sections = []
        for section in self.pe.sections:
            try:
                name = self.process_binary_string(section.Name)
            except Exception as e:
                name = "UnableToDecode"
                self.log.warning(
                    f'Unable to store section Name "{section.Name}" for {self.hash.sha256}'
                    f" exception {e}"
                )
            sec_sha256 = section.get_hash_sha256()
            sec_md5 = section.get_hash_md5()
            # sec_entropy = "%.2f" % section.get_entropy()
            sec_entropy = section.get_entropy()
            pe_section = PESection(
                _id=hashlib.sha256(
                    name.encode()
                ).hexdigest(),  # usecase 8e035beb02a411f8a9e92d4cf184ad34f52bbd0a81a50c222cdd4706e4e45104, all section have same sha256
                section_name=name,
                section_name_b64=base64.b64encode(
                    section.Name.rstrip(b'\x00')
                ).decode(),  # base64.b64decode(b64) to decode
                section_v_addr=section.VirtualAddress,
                section_v_addr_hex=hex(section.VirtualAddress),
                section_v_size=section.Misc_VirtualSize,
                section_size=section.SizeOfRawData,
                section_pointer_to_raw_data=hex(section.PointerToRawData),
                section_md5=sec_md5,
                section_sha256=sec_sha256,
                section_entropy=sec_entropy,
            )
            sections.append(pe_section)
        return sections

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

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.extract()
        elif exporter_type == "ClickHouseExporter":
            sections = self.extract()
            if sections is None:
                return None
            
            data = []
            current_time = datetime.now(timezone.utc)
            
            for section in sections:
                data.append([
                    self.sha256,                          # sha256
                    self.md5,                             # md5
                    self.sha1,                            # sha1
                    section.section_name,                 # section_name
                    section.section_name_b64,             # section_name_b64
                    section.section_entropy,              # section_entropy
                    section.section_sha256,               # section_sha256
                    section.section_md5,                  # section_md5
                    section.section_size,                 # section_size
                    section.section_v_addr,               # section_v_addr
                    section.section_v_size,               # section_v_size
                    int(section.section_pointer_to_raw_data, 16),  # section_pointer_to_raw_data - convert from hex
                    current_time                          # analysis_date
                ])
            
            column_names = [
                'sha256', 'md5', 'sha1', 'section_name', 'section_name_b64',
                'section_entropy', 'section_sha256', 'section_md5', 'section_size',
                'section_v_addr', 'section_v_size', 'section_pointer_to_raw_data',
                'analysis_date'
            ]
            
            if not data:
                return None

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

            return (data, column_names, column_type_names)

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