Hai Xiao

30 papers A 1Misc 1Journal 24Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Pattern Recognit.
Yalu Zhang, Sixiang Quan, Hai Xiao, Jun Liu, Zhenfeng Shao, Zhihui Wang, Yingying Peng, Huali Li
2026 J jnl
CoRR
Bangchen Yin, Jian Ouyang, Zhen Fan, Kailai Lin, Hanshi Hu, Dingshun Lv, Weiluo Ren, Hai Xiao, Ji Chen, Changsu Cao
2026 J jnl
Geo spatial Inf. Sci.
Zhizheng Zhang, Pengcheng Wei, Zhenfeng Shao, Hai Xiao, Qingwei Zhuang, Zhiqing Tang, Zhijun Wen, Yu Wang, Yuyan Yan, Mingqiang Guo
2025 J jnl
CoRR
Bangchen Yin, Jiaao Wang, Weitao Du, Pengbo Wang, Penghua Ying, Haojun Jia, Zisheng Zhang, Yuanqi Du, Carla P. Gomes, Chenru Duan, Hai Xiao, Graeme Henkelman
2025 J jnl
IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens.
Zeyang Wei, Hai Xiao, Lu Zhang, Lifei Wei, Qikai Lu
2025 conf
I2MTC
Yongji Wu, Jing Guo, Xinyu Jiao, Ningxuan Wen, Ruan Li, Jason Shaw, Fei Peng, Hai Xiao
2024 J jnl
CoRR
Bangchen Yin, Yue Yin, Yuda W. Tang, Hai Xiao
2024 conf
I2MTC
Xinyu Jiao, Yongji Wu, Huijuan Zhao, Dock R. Houston, Dustin Gravley, Susan Maley, Chethan K. Acharya, Hai Xiao
2024 J jnl
Sensors
Tanuj Gupta, Mahabubur Rahman, Xinyu Jiao, Yongji Wu, Chethan K. Acharya, Dock R. Houston, Susan Maley, Junhang Dong, Hai Xiao, Huijuan Zhao
2023 J jnl
Remote. Sens.
Mengting Sang, Hai Xiao, Zhili Jin, Junchen He, Nan Wang, Wei Wang
2022 conf
IEEE SENSORS
Xuran Zhu, Qi Zhang, Mark Matlin, Yizheng Chen, Ying Yang, Tingxuan Li, Wenge Zhu, Yongji Wu, Huijuan Zhao, Rich Pollack, Marek Urban, Hai Xiao
2022 J jnl
Reliab. Eng. Syst. Saf.
Jianlan Zhou, Ren-Fang Tu, Hai Xiao
2021 J jnl
Sensors
Liwei Hua, Xuran Zhu, Baokai Cheng, Yang Song, Qi Zhang, Yongji Wu, Lawrence C. Murdoch, Erin R. Dauson, Carly M. Donahue, Hai Xiao
2021 J jnl
IEEE Trans. Ind. Informatics
Zhuoli Zhao, Juntao Guo, Chun Sing Lai, Hai Xiao, Keyu Zhou, Loi Lei Lai
2020 J jnl
CoRR
Hai Xiao, Jin Shang, Mengyuan Huang
2020 A conf
AsiaCCS
Fei Ding, Hongda Li, Feng Luo, Hongxin Hu, Long Cheng, Hai Xiao, Rong Ge
2019 J jnl
Signal Process. Image Commun.
Lei Wang, Hai Xiao, Sheng Luo, Jie Zhang, Xiyao Liu
2019 J jnl
CoRR
Hai Xiao
2018 J jnl
Sensors
Zhihui Pan, Ying Huang, Hai Xiao
2018 conf
OFC
Xiaobei Zhang, Jiawei Wang, Ming Yan, Hai Xiao, Tingyun Wang
2016 J jnl
J. Sensors
Yang Song, Liwei Hua, Jincheng Lei, Qi Zhang, Jie Liu, Lingyun Ye, Hai Xiao
2016 J jnl
Sensors
Zhi Zhou, Tong Jiao, Peng Zhao, Jia Liu, Hai Xiao
2015 J jnl
Sensors
Adam Trontz, Baokai Cheng, Shixuan Zeng, Hai Xiao, Junhang Dong
2013 J jnl
Sensors
Jie Huang, Tao Wang, Lei Hua, Jun Fan, Hai Xiao, Ming Luo
2011 J jnl
Sensors
Longjiang Zhao, Lan Jiang, Sumei Wang, Hai Xiao, Yongfeng Lu, Hai-Lung Tsai
2011 J jnl
Sensors
Benye Li, Lan Jiang, Sumei Wang, Lanying Zhou, Hai Xiao, Hai-Lung Tsai
2010 J jnl
IEEE Trans. Instrum. Meas.
Ying Huang, Zhi Zhou, Yinan Zhang, Genda Chen, Hai Xiao
2009 Misc conf
ICISS
Ping Chen, Hai Xiao, Xiaobin Shen, Xinchun Yin, Bing Mao, Li Xie
2009 J jnl
IEEE Signal Process. Mag.
Zhiyong Wang, Hai Xiao
2005 J jnl
IEICE Trans. Electron.
Hai Xiao, Takayuki Tanaka, Masayoshi Aikawa
redb/extractors/elf_extractors/elf_imports.py
← Index redb/extractors/elf_extractors/elf_imports.py python
import inspect
from datetime import datetime, timezone
from typing import Any, List, Set

from elftools.elf.elffile import ELFFile
from elftools.common.exceptions import ELFError

from redb.extractors.enum import Tag
from redb.extractors.elf_extractor import ELFExtractor
from redb.models.dataclasses import ELFImport


class ELFImportExtractor(ELFExtractor):

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

    def _get_import_libraries(self, elf) -> List[str]:
        """Extract imported libraries from dynamic section."""
        libraries = []

        try:
            # Get the dynamic section
            dynamic_section = elf.get_section_by_name('.dynamic')
            if not dynamic_section:
                return libraries

            # Extract DT_NEEDED entries (required libraries)
            for tag in dynamic_section.iter_tags():
                if tag.entry.d_tag == 'DT_NEEDED':
                    libraries.append(tag.needed)

        except Exception as e:
            self.log.error(f"Error extracting import libraries: {e}")

        return libraries

    def _get_imported_functions_from_symbols(self, elf) -> Set[str]:
        """Extract imported functions from dynamic symbol table."""
        imported_functions = set()

        try:
            # Get the dynamic symbol table
            dynsym_section = elf.get_section_by_name('.dynsym')
            if not dynsym_section or not hasattr(dynsym_section, 'iter_symbols'):
                return imported_functions

            # Look for undefined symbols (imports)
            for symbol in dynsym_section.iter_symbols():
                # Check if symbol is undefined (imported)
                if (symbol.entry.get('st_shndx', 0) == 'SHN_UNDEF' and
                    symbol.name and
                    symbol.entry.get('st_info', {}).get('bind') in ['STB_GLOBAL', 'STB_WEAK']):
                    imported_functions.add(symbol.name)

        except Exception as e:
            self.log.error(f"Error extracting imported functions from symbols: {e}")

        return imported_functions

    def _get_imported_functions_from_relocations(self, elf) -> Set[str]:
        """Extract imported functions from relocation sections."""
        imported_functions = set()

        try:
            # Look through relocation sections
            for section in elf.iter_sections():
                if hasattr(section, 'iter_relocations'):
                    try:
                        for relocation in section.iter_relocations():
                            # Get symbol associated with relocation
                            if hasattr(relocation, 'symbol') and relocation.symbol:
                                symbol_name = relocation.symbol.name
                                if symbol_name:
                                    imported_functions.add(symbol_name)
                    except Exception as e:
                        self.log.debug(f"Could not process relocations in section {section.name}: {e}")

        except Exception as e:
            self.log.error(f"Error extracting imported functions from relocations: {e}")

        return imported_functions

    def _get_plt_functions(self, elf) -> Set[str]:
        """Extract functions from PLT (Procedure Linkage Table) sections."""
        plt_functions = set()

        try:
            # Look for PLT-related sections
            plt_sections = ['.plt', '.plt.got', '.plt.sec']

            for section_name in plt_sections:
                section = elf.get_section_by_name(section_name)
                if section:
                    # PLT functions are typically associated with relocations
                    # We'll get them from the relocation analysis
                    pass

        except Exception as e:
            self.log.error(f"Error extracting PLT functions: {e}")

        return plt_functions

    def tag(self):
        return Tag.ELF_IMPORTS.value if hasattr(Tag, 'ELF_IMPORTS') else "elf_imports"

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

            def extract_data(elf):
                # Extract import libraries
                import_libraries = self._get_import_libraries(elf)

                # Extract imported functions from multiple sources
                imported_functions = set()

                # From dynamic symbols
                symbol_imports = self._get_imported_functions_from_symbols(elf)
                imported_functions.update(symbol_imports)

                # From relocations
                relocation_imports = self._get_imported_functions_from_relocations(elf)
                imported_functions.update(relocation_imports)

                # From PLT
                plt_imports = self._get_plt_functions(elf)
                imported_functions.update(plt_imports)

                # Convert to sorted lists for consistent output
                import_libraries_list = sorted(list(set(import_libraries)))
                import_functions_list = sorted(list(imported_functions))

                # Return ELFImport dataclass
                return ELFImport(
                    elf_imports_total=len(import_functions_list),
                    elf_import_libraries=import_libraries_list,
                    elf_import_functions=import_functions_list,
                )

            if not self._is_elf_file():
                return None

            result = self._with_elf_file(extract_data)
            if result is None:
                return None

            self.elf_imports = result
            return self.elf_imports

        except Exception as e:
            self.log.error(f"Error extracting ELF imports {self.hash.sha256}: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        self.log.debug(inspect.currentframe().f_code.co_name)

        if exporter_type == "ElasticsearchExporter":
            return self.elf_imports
        elif exporter_type == "ClickHouseExporter":
            try:
                if not self.elf_imports:
                    return None

                # Prepare data array
                data = [[
                    self.sha256,
                    self.md5,
                    self.sha1,
                    self.elf_imports.elf_imports_total,
                    self.elf_imports.elf_import_libraries,
                    self.elf_imports.elf_import_functions,
                    datetime.now(timezone.utc)
                ]]

                column_names = [
                    'sha256', 'md5', 'sha1',
                    'elf_imports_total',
                    'elf_import_libraries',
                    'elf_import_functions',
                    'analysis_date'
                ]

                column_type_names = [
                    'FixedString(64)', 'FixedString(32)', 'FixedString(40)',
                    'UInt32',
                    'Array(LowCardinality(String))',
                    'Array(LowCardinality(String))',
                    'DateTime64(3, \'UTC\')'
                ]

                if not data:
                    return None

                return (data, column_names, column_type_names)

            except Exception as e:
                self.log.error(f"Error preparing export data: {e}")
                raise

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