Xiao Li

33 papers C 2Misc 1Journal 16Unranked 14
YearRankTypeTitle / Venue / Authors
2021 J jnl
Inf.
Yajuan Wang, Xiao Li, Yating Yang, Azmat Anwar, Rui Dong
2021 J jnl
Inf.
Wenbo Zhang, Xiao Li, Yating Yang, Rui Dong
2020 J jnl
Inf.
Yu Li, Xiao Li, Yating Yang, Rui Dong
2020 conf
ICIC (2)
Xiao-Rui Su, Zhu-Hong You, Ji-Ren Zhou, Hai-Cheng Yi, Xiao Li
2020 conf
CNCL
Azmat Anwar, Xiao Li, Yating Yang, Rui Dong, Osman Turghun
2020 J jnl
IEEE Access
Xinlu Zhang, Xiao Li, Yating Yang, Rui Dong
2020 J jnl
Future Internet
Wenbo Zhang, Xiao Li, Yating Yang, Rui Dong, Gongxu Luo
2020 J jnl
CoRR
Yirong Pan, Xiao Li, Yating Yang, Rui Dong
2020 J jnl
Future Internet
Yirong Pan, Xiao Li, Yating Yang, Rui Dong
2020 conf
ACL (student)
Yirong Pan, Xiao Li, Yating Yang, Rui Dong
2020 conf
ICIC (2)
Bo-Wei Zhao, Ping Zhang, Zhu-Hong You, Ji-Ren Zhou, Xiao Li
2020 J jnl
Inf.
Yang Yuan, Xiao Li, Yating Yang
2019 conf
NLPCC (2)
Yajuan Wang, Xiao Li, Yating Yang, Azmat Anwar, Rui Dong
2018 J jnl
Complex.
Yanbin Wang, Zhuhong You, Liping Li, Li Cheng, Xi Zhou, Libo Zhang, Xiao Li, Tonghai Jiang
2018 J jnl
BMC Syst. Biol.
Yan-Bin Wang, Zhu-Hong You, Xiao Li, Tong-Hai Jiang, Li Cheng, Zhan-Heng Chen
2018 conf
ICIC (2)
Zhan-Heng Chen, Zhu-Hong You, Liping Li, Yan-Bin Wang, Xiao Li
2017 conf
CWMT
Yirong Pan, Xiao Li, Yating Yang, Chenggang Mi, Rui Dong, Wenxiao Zeng
2017 J jnl
Neurocomputing
Zhu-Hong You, Xiao Li, Keith C. C. Chan
2017 conf
IALP
Shaolin Zhu, Yating Yang, Xiao Li, Tonghai Jiang, Lei Wang, Xi Zhou, Chenggang Mi
2017 conf
CCL
Shaolin Zhu, Xiao Li, Yating Yang, Lei Wang, Chenggang Mi
2017 conf
GlobalSIP
Yating Yang, Xiao Li, Tonghai Jiang, Jinying Kong, Bo Ma, Xi Zhou, Lei Wang
2017 conf
NLPCC
Shaolin Zhu, Xiao Li, Yating Yang, Lei Wang, Chenggang Mi
2017 Misc conf
RANLP
Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang
2017 J jnl
IEEE ACM Trans. Comput. Biol. Bioinform.
Jian-Qiang Li, Zhu-Hong You, Xiao Li, Zhong Ming, Xing Chen
2017 J jnl
J. Inf. Process. Syst.
Alim Murat, Osman Turghun, Yating Yang, Xi Zhou, Lei Wang, Xiao Li
2016 J jnl
Neurocomputing
Yu-An Huang, Zhu-Hong You, Xiao Li, Xing Chen, Pengwei Hu, Shuai Li, Xin Luo
2016 J jnl
Computación y Sistemas
Chenggang Mi, Yating Yang, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang
2016 C conf
PACLIC
Chenggang Mi, Yating Yang, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang
2016 conf
NLPCC/ICCPOL
Jinying Kong, Yating Yang, Xi Zhou, Lei Wang, Xiao Li
2015 C conf
NLDB
Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang, Osman Turghun
2014 J jnl
J. Comput.
Chenggang Mi, Yating Yang, Xi Zhou, Lei Wang, Xiao Li, Eziz Tursun
2014 conf
CCL
Chenggang Mi, Yating Yang, Xi Zhou, Xiao Li, Osman Turghun
2014 conf
NLPCC
Chenggang Mi, Yating Yang, Lei Wang, Xiao Li, Kamali Dalielihan
redb/extractors/macho_extractors/macho_dylibs.py
← Index redb/extractors/macho_extractors/macho_dylibs.py python
import hashlib
import inspect
from datetime import datetime, timezone
from typing import Any

from redb.extractors.enum import Tag
from redb.extractors.macho_extractor import MachOExtractor
from redb.models.dataclasses import MachODylib


class MachODylibExtractor(MachOExtractor):

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

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

    def _extract_dylibs(self):
        """Extract dynamic library information from all architectures in the MachO binary."""
        self.log.debug(inspect.currentframe().f_code.co_name)
        dylibs = []

        if not self.macho:
            return dylibs

        try:
            # Get architectures using new API (already parsed in base class)
            architectures = self.macho.get_architectures()
            if not architectures:
                return dylibs

            # Process each architecture
            for arch_name in architectures:
                # Get dylib commands using new API with architecture parameter
                dylib_commands = self.macho.get_dylib_commands(arch=arch_name)
                if not dylib_commands:
                    continue

                # Extract dylib commands for this architecture
                for dylib_cmd in dylib_commands:
                    try:
                        dylib_name = dylib_cmd.get('dylib_name', 'Unknown')
                        if isinstance(dylib_name, bytes):
                            dylib_name = dylib_name.decode('utf-8', errors='replace')

                        # Create dylib dataclass with architecture info
                        macho_dylib = MachODylib(
                            dylib_name=dylib_name,
                            dylib_timestamp=dylib_cmd.get('dylib_timestamp', 0),
                            dylib_current_version=dylib_cmd.get('dylib_current_version', 0),
                            dylib_compat_version=dylib_cmd.get('dylib_compat_version', 0),
                        )
                        # Add architecture info to the dylib
                        macho_dylib.architecture = arch_name
                        dylibs.append(macho_dylib)

                    except Exception as e:
                        self.log.warning(
                            f'Unable to process dylib "{dylib_cmd.get("dylib_name", "Unknown")}" for architecture {arch_name} in {self.hash.sha256}: {e}'
                        )
                        continue

            return dylibs

        except Exception as e:
            self.log.error(f"Error extracting MachO dylibs: {e}")
            return dylibs

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            dylibs = self._extract_dylibs()
            return dylibs
        except Exception as e:
            self.log.error(f"Error extracting MachO dylibs: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.extract()
        elif exporter_type == "ClickHouseExporter":
            if not self.macho:
                return None

            # Get architectures (macho is already parsed in base class)
            try:
                architectures = self.macho.get_architectures()
                is_fat = len(architectures) > 1
            except Exception as e:
                self.log.error(f"Could not get architectures: {e}")
                return None

            data = []
            current_time = datetime.now(timezone.utc)

            # Loop through each architecture (1 for single, multiple for FAT)
            for arch_name in architectures:
                # Get architecture-specific sha256
                try:
                    arch_general_info = self.macho.get_general_info(arch=arch_name)
                    arch_header_raw = self.macho.get_macho_header(arch=arch_name)
                    arch_sha256 = arch_general_info.get('SHA256', self.sha256)
                    arch_cputype_raw = arch_header_raw.get('cputype', 0) if arch_header_raw else 0
                except Exception as e:
                    self.log.warning(f"Could not get arch-specific data for {arch_name}: {e}")
                    arch_sha256 = self.sha256
                    arch_cputype_raw = 0

                # Get dylib commands for this architecture
                dylib_commands = self.macho.get_dylib_commands(arch=arch_name)
                if not dylib_commands:
                    continue

                # Process each dylib for this architecture
                for dylib_cmd in dylib_commands:
                    try:
                        dylib_name = dylib_cmd.get('dylib_name', 'Unknown')
                        if isinstance(dylib_name, bytes):
                            dylib_name = dylib_name.decode('utf-8', errors='replace')

                        data.append([
                            arch_sha256,                          # sha256 (architecture-specific)
                            dylib_name,                           # dylib_name
                            dylib_cmd.get('dylib_timestamp', 0), # dylib_timestamp
                            dylib_cmd.get('dylib_current_version', 0), # dylib_current_version
                            dylib_cmd.get('dylib_compat_version', 0),  # dylib_compat_version
                            current_time,                         # analysis_date
                        ])
                    except Exception as e:
                        self.log.warning(
                            f'Unable to process dylib "{dylib_cmd.get("dylib_name", "Unknown")}" for architecture {arch_name}: {e}'
                        )
                        continue

            column_names = [
                'sha256',
                'dylib_name', 'dylib_timestamp', 'dylib_current_version',
                'dylib_compat_version', 'analysis_date'
            ]

            if not data:
                return None

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

            return (data, column_names, column_type_names)

        return None

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