Haeun Lee

11 papers A* 3C 2Journal 3Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
J. Biomed. Informatics
Haeun Lee, Christelle Xiong, Derek Baughman, Chen Dun, Jiayi Tong, Benjamin Martin, Harold P. Lehmann, Paul G. Nagy
2026 conf
CHI Extended Abstracts
Haeun Lee, Jaehun Huh, Sungwoo Han, Gyuwon Jung, Jaejeung Kim
2025 A* conf
WWW
Sungjun Jung, Yongsang Park, Haeun Lee, Young H. Oh, Jae W. Lee
2025 J jnl
CoRR
Haeun Lee, Omin Kwon, Yeonhong Park, Jae W. Lee
2025 conf
ISSTA Companion
Jungwoo Lee, Haeun Lee, Sangjun Park, Sang Kil Cha
2024 C conf
SERA
SeongGyeol Park, Ahtae Kim, SooKyung Lee, Haeun Lee, Chayapol Kamyod, Cheong Ghil Kim
2024 conf
ESORICS Workshops (2)
Sanghyun Park, Haeun Lee, Sang Kil Cha
2023 C conf
APSEC
Haeun Lee, HeeDong Yang, Su Geun Ji, Sang Kil Cha
2022 A* conf
ASE
Haeun Lee, Soomin Kim, Sang Kil Cha
2022 A* conf
UIST
Kongpyung (Justin) Moon, Haeun Lee, Jeeeun Kim, Andrea Bianchi
2020 J jnl
J. Digit. Imaging
KyeongTaek Oh, Sangwon Lee, Haeun Lee, Mijin Yun, Sun K. Yoo
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"