Katarina Boland

26 papers B 2Journal 6Unranked 17
YearRankTypeTitle / Venue / Authors
2026 conf
ECIR (4)
Johannes Kiesel, Marc Feger, Tim Hagen, Sebastian Heineking, Maximilian Heinrich, Maik Fröbe, Katarina Boland, Wilhelm Pertsch, Julia Romberg, Ines Zelch, Stefan Dietze, Matthias Hagen, Martin Potthast, Benno Stein
2025 conf
ACL (1)
Marc Feger, Katarina Boland, Stefan Dietze
2025 J jnl
CoRR
Marc Feger, Katarina Boland, Stefan Dietze
2025 conf
CLEF (Working Notes)
Salim Hafid, Yavuz Selim Kartal, Sebastian Schellhammer, Katarina Boland, Dimitar Dimitrov, Sandra Bringay, Konstantin Todorov, Stefan Dietze
2025 conf
CLEF (Working Notes)
Philipp Meier, Katarina Boland, Laura Kallmeyer, Stefan Dietze
2024
Katarina Boland
2024 J jnl
CoRR
Katarina Boland, Christopher Starke, Felix Bensmann, Frank Marcinkowski, Stefan Dietze
2023 conf
D2R2
Susmita Gangopadhyay, Katarina Boland, Danilo Dessì, Stefan Dietze, Pavlos Fafalios, Andon Tchechmedjiev, Konstantin Todorov, Hajira Jabeen
2022 J jnl
Semantic Web
Katarina Boland, Pavlos Fafalios, Andon Tchechmedjiev, Stefan Dietze, Konstantin Todorov
2022 conf
CLEF (Working Notes)
Alica Hövelmeyer, Katarina Boland, Stefan Dietze
2021 conf
WWW (Companion Volume)
Evangelos Maliaroudakis, Katarina Boland, Stefan Dietze, Konstantin Todorov, Yannis Tzitzikas, Pavlos Fafalios
2021 J jnl
Neurocomputing
Xiaofei Zhu, Jie Wu, Ling Zhu, Jiafeng Guo, Ran Yu, Katarina Boland, Stefan Dietze
2020 conf
Insights
Valentina Beretta, Sébastien Harispe, Katarina Boland, Luke Lo Seen, Konstantin Todorov, Andon Tchechmedjiev
2019 conf
JCDL
Daniel Hienert, Dagmar Kern, Katarina Boland, Benjamin Zapilko, Peter Mutschke
2019 J jnl
CoRR
Daniel Hienert, Dagmar Kern, Katarina Boland, Benjamin Zapilko, Peter Mutschke
2019 conf
ISWC (2)
Andon Tchechmedjiev, Pavlos Fafalios, Katarina Boland, Malo Gasquet, Matthäus Zloch, Benjamin Zapilko, Stefan Dietze, Konstantin Todorov
2019 conf
BIRNDL@SIGIR
Katarina Boland, Frank Krüger
2019 conf
ISWC (Satellites)
Malo Gasquet, Darlene Brechtel, Matthäus Zloch, Andon Tchechmedjiev, Katarina Boland, Pavlos Fafalios, Stefan Dietze, Konstantin Todorov
2019 conf
BlockSW/CKG@ISWC
Katarina Boland, Pavlos Fafalios, Andon Tchechmedjiev, Konstantin Todorov, Stefan Dietze
2018 B conf
ESWC
Benjamin Zapilko, Katarina Boland, Dagmar Kern
2015 J jnl
D Lib Mag.
Brigitte Mathiak, Katarina Boland
2013 conf
IASSIST Conference
Katarina Boland, Brigitte Mathiak
2013 conf
Dublin Core Conference
Dominique Ritze, Katarina Boland
2013 conf
IASSIST Conference
Dimitar Dimitrov, Daniel Hienert, Katarina Boland, Dennis Wegener
2012 B conf
TPDL
Katarina Boland, Dominique Ritze, Kai Eckert, Brigitte Mathiak
2011 conf
KES (4)
Stephanie Schuldes, Katarina Boland, Michael Roth, Michael Strube, Susanne Krömker, Anette Frank
redb/extractors/pe_extractors/pe_imports.py
← Index redb/extractors/pe_extractors/pe_imports.py python
import inspect
from typing import Any, List, Tuple
from datetime import datetime, timezone

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


class PEImportExtractor(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_imports"
        self.log.debug(inspect.currentframe().f_code.co_name)

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

    def _extract_imports(self):
        self.log.debug(inspect.currentframe().f_code.co_name)

        imports_symbols = []
        imports_lib = []
        imports_total = 0
        # pe_import = None
        try:
            directory_entry_import = getattr(self.pe, "DIRECTORY_ENTRY_IMPORT", [])
            imports_total = len(directory_entry_import)
            for entry in directory_entry_import:
                symbols = []
                tmp_import = {}
                libname = entry.dll.decode() if entry.dll else ""
                imports_lib.append(libname)
                # replace . with _ to avoid issues with elastic
                # entryname = entryname.replace(".", "_")
                for symbol in entry.imports:
                    if symbol.name:
                        symbols.append(symbol.name.decode())
                # imports_symbols[entryname] = symbols
                tmp_import[libname] = symbols
                imports_symbols.append(tmp_import)
            return PEImport(
                pe_imports_total=imports_total,
                pe_import_libraryName=imports_lib if imports_lib else None,
                pe_import_functions=imports_symbols if imports_symbols else None,
            )
        except Exception as e:
            self.log.error(f"Extract imports error {self.hash.sha256} Exception: {e}")
        return pe_import

    def extract(self):
        try:
            self.log.debug(inspect.currentframe().f_code.co_name)
            return self._extract_imports()
        except Exception as e:
            self.log.error(f"Extract imports error {self.hash.sha256} Exception: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.extract()
        elif exporter_type == "ClickHouseExporter":
            imports = self.extract()
            if (
                imports is None
                or imports.pe_imports_total == 0
                or (
                    imports.pe_import_libraryName is None
                    and imports.pe_import_functions is None
                )
            ):
                return None

            # Flatten the data - one row per function import
            data = []
            current_time = datetime.now(timezone.utc)

            for lib_funcs in imports.pe_import_functions:
                for lib, funcs in lib_funcs.items():
                    for func in funcs:
                        data.append(
                            [
                                self.sha256,  # sha256
                                self.md5,  # md5
                                self.sha1,  # sha1
                                lib,  # library_name
                                func,  # function_name
                                current_time,  # analysis_date
                            ]
                        )

            column_names = [
                "sha256",
                "md5",
                "sha1",
                "library_name",
                "function_name",
                "analysis_date",
            ]

            column_type_names = [
                "FixedString(64)",
                "FixedString(32)",
                "FixedString(40)",
                "LowCardinality(Nullable(String))",
                "LowCardinality(Nullable(String))",
                "DateTime64(3, 'UTC')",
            ]

            if not data:
                return None

            return (data, column_names, column_type_names)

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