Kaihua Cao

20 papers A* 1A 1C 1Journal 10Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Sci. China Inf. Sci.
Jialiang Yin, Xiuye Zhang, Boyan Zhang, Bolin Zhang, Wenlong Cai, Ao Du, Binchao Tang, Haowei Zhang, Shijian Bao, Chunyi Li, Daoqian Zhu, Kewen Shi, Hongxi Liu, Lang Zeng, He Zhang, Kaihua Cao, Weisheng Zhao
2025 A conf
ICCAD
Liangchen Li, Jianxin Wu, Changyu Li, Liang Zhang, Anyang Yu, Junda Zhao, Zhaohao Wang, Chengyuan Sun, Kaihua Cao, Hongxi Liu, Wang Kang, He Zhang, Weisheng Zhao
2025 J jnl
Sci. China Inf. Sci.
Yuxuan Yao, Daoqian Zhu, Qingtao Xia, Jianing Liang, Yuhao Jiang, Zhiyang Peng, Jiaxu Li, Chen Xiao, Renyou Xu, Wenwen Wang, Xiantao Shang, Shiyang Lu, Dapeng Zhu, Hongxi Liu, Kaihua Cao, Weisheng Zhao
2025 conf
MOCAST
Tuo Zhang, Xinpeng Jiang, Chao Wang, Bi Wang, Hongxi Liu, Kaihua Cao, Xuan Li, Hui Jin, Geifei Wang, Zhaohao Wang, He Zhang, Weisheng Zhao
2024 conf
APCCAS
Zhaohao Wang, Chao Wang, Min Wang, Chenyi Wang, Kaihua Cao, Chenlin Xu, Cong Zhang, Yunpeng Li, Hongxi Liu
2024 A* conf
DAC
Weiliang Huang, Jinyu Bai, Wang Kang, Zhaohao Wang, Kaihua Cao, Hongxi Liu, He Zhang, Weisheng Zhao
2024 J jnl
Sci. China Inf. Sci.
Shiyang Lu, Xiaobai Ning, Hongchao Zhang, Sixi Zhen, Xiaofei Fan, Danrong Xiong, Dapeng Zhu, Gefei Wang, Hongxi Liu, Kaihua Cao, Weisheng Zhao
2023 conf
IRPS
Xinyi Xu, Hongchao Zhang, Chuanpeng Jiang, Jinhao Li, Shiyang Lu, Yunpeng Li, Honglei Du, Xueying Zhang, Zhaohao Wang, Kaihua Cao, Weisheng Zhao, Shuqin Lyu, Hao Xu, Bonian Jiang, Le Wang, Bowen Man, Cong Zhang, Dandan Li, Shuhui Li, Xiaofei Fan, Gefei Wang, Hongxi Liu
2023 J jnl
Sci. China Inf. Sci.
Yan Huang, Kaihua Cao, Kun Zhang, Jinkai Wang, Kewen Shi, Zuolei Hao, Wenlong Cai, Ao Du, Jialiang Yin, Qing Yang, Junfeng Li, Jianfeng Gao, Chao Zhao, Weisheng Zhao
2023 J jnl
Peer Peer Netw. Appl.
Xuewen He, Kaihua Cao
2022 J jnl
Sci. China Inf. Sci.
Luding Wang, Wenlong Cai, Kaihua Cao, Kewen Shi, Bert Koopmans, Weisheng Zhao
2022 J jnl
Sci. China Inf. Sci.
Wenlong Cai, Mengxing Wang, Kaihua Cao, Huaiwen Yang, Shouzhong Peng, Huisong Li, Weisheng Zhao
2021 J jnl
Proc. IEEE
Zongxia Guo, Jialiang Yin, Yue Bai, Daoqian Zhu, Kewen Shi, Gefei Wang, Kaihua Cao, Weisheng Zhao
2019 J jnl
IEEE Trans. Circuits Syst. I Regul. Pap.
Bi Wang, Zhaohao Wang, Bi Wu, Yumeng Bai, Kaihua Cao, Yuanfu Zhao, Youguang Zhang, Weisheng Zhao
2019 conf
ASICON
Zongxia Guo, Kaihua Cao, Kewen Shi, Weisheng Zhao
2018 C conf
ISCAS
Bi Wang, Zhaohao Wang, Kaihua Cao, Youguang Zhang, Yuanfu Zhao, Weisheng Zhao
2017 conf
NVMTS
Wenlong Cai, Kaihua Cao, Mengxing Wang, Shouzhong Peng, Jiaqi Zhou, Anni Cao, Boyu Zhang, Lezhi Wang, Yu Zhang, Jiaqi Wei, Xiaobin He, Hushan Cui, Chao Zhao, Weisheng Zhao
2017 conf
ASICON
Jiaqi Wei, Liang Chang, Zhaohao Wang, Xiaoyang Lin, Kaihua Cao, Hushan Cui, Wang Kang, Haoxuan Chen, Lang Zeng, Youguang Zhang, Chao Zhao, Weisheng Zhao
2016 J jnl
IEEE Trans. Biomed. Circuits Syst.
Deming Zhang, Lang Zeng, Kaihua Cao, Mengxing Wang, Shouzhong Peng, Yue Zhang, Youguang Zhang, Jacques-Olivier Klein, Yu Wang, Weisheng Zhao
2015 conf
ASICON
Kaihua Cao, Heng Zhao, Mengxing Wang, Weisheng Zhao
redb/extractors/basicproperties.py
← Index redb/extractors/basicproperties.py python
from dataclasses import asdict
import inspect
import os
import magic
from magika import Magika
from datetime import datetime, timezone
from typing import Any, List, Tuple

from redb.extractors.enum import Tag
from redb.models.dataclasses import BasicProperties
from redb.extractors.extractor import Extractor


class BasicPropertiesExtractor(Extractor):

    def __init__(
        self,
        filepath,
        log,
        exporters=None,
        index_prefix=None,
        elastic_index=None,
        known_benign=False,
        known_malicious=False,
        parent_sha256=None,
        precomputed_hashes=None,
        is_fat=None,
        child_sha256=None,
        child_architecture=None,
        child_filetype=None,
        first_seen=None,
    ):
        super().__init__(
            filepath,
            log,
            exporters=exporters,
            index_prefix=index_prefix,
            elastic_index=elastic_index,
            known_benign=known_benign,
            known_malicious=known_malicious,
            precomputed_hashes=precomputed_hashes,
        )
        self.basic_properties = None
        self.elastic_index = self.index_prefix + "-basic_properties"
        self.is_packed = None
        self.parent_sha256 = parent_sha256  # For FAT Mach-O slices, points to container hash
        self.is_fat = is_fat  # True for FAT Mach-O containers, None otherwise
        self.child_sha256 = child_sha256  # SHA256 hashes of children (FAT slices, zip contents)
        self.child_architecture = child_architecture  # Architecture names for FAT Mach-O slices
        self.child_filetype = child_filetype  # Magika filetypes for children (useful for zip archives)
        self.first_seen = first_seen  # From catalog_samples, None for local files

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

    def _extract_basic_properties(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        filename = None  # Reserved for future use
        sample_name = os.path.basename(self.filepath)
        file_entropy = round(self.calculate_entropy(self.binary), 3)
        type_ = magic.from_buffer(self.binary)
        type_mime = magic.from_buffer(self.binary, mime=True)
        type_magika = Magika().identify_bytes(self.binary).output.label
        size = len(self.binary)
        self.basic_properties = BasicProperties(
            filename, sample_name, size, type_, type_mime, type_magika,
            file_entropy, self.is_packed, self.is_fat, self.child_sha256,
            self.child_architecture, self.child_filetype,
            first_seen=str(self.first_seen) if self.first_seen else None,
        )
        self.log.debug(f"Basic Properties dump: {asdict(self.basic_properties)}")

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            self._extract_basic_properties()
            # self.export_to_elastic([self.basic_properties])
            return self.basic_properties
        except Exception as e:
            self.log.error(f"Extract basic properties error {self.hash.sha256} Exception: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.basic_properties
        elif exporter_type == "ClickHouseExporter":
            data = [[
                self.sha256,
                self.md5,
                self.sha1,
                self.parent_sha256,  # NULL for standalone/FAT, fat_hash for slices
                self.basic_properties.child_sha256 or [],  # SHA256 hashes of children
                self.basic_properties.child_architecture or [],  # Architecture names for FAT slices
                self.basic_properties.child_filetype or [],  # Magika filetypes for children
                self.basic_properties.is_fat,  # True for FAT Mach-O containers, NULL otherwise
                self.basic_properties.filename,
                self.basic_properties.sample_name,
                self.basic_properties.filesize,
                self.basic_properties.file_entropy,
                self.basic_properties.filetype,
                self.basic_properties.filetype_mime,
                self.basic_properties.filetype_magika,
                self.first_seen or datetime(1970, 1, 1, tzinfo=timezone.utc),  # From catalog_samples, epoch zero for local files (uses original datetime, not string)
                datetime.now(timezone.utc)
            ]]

            column_names = [
                'sha256', 'md5', 'sha1', 'parent_sha256', 'child_sha256', 'child_architecture', 'child_filetype',
                'is_fat', 'filename', 'sample_name',
                'filesize', 'file_entropy', 'filetype', 'filetype_mime',
                'filetype_magika', 'first_seen', 'analysis_date'
            ]

            column_type_names = [
                'String', 'String', 'String', 'Nullable(String)',
                'Array(FixedString(64))', 'Array(LowCardinality(String))', 'Array(LowCardinality(String))',
                'Nullable(UInt8)', 'Nullable(String)', 'String',
                'UInt64', 'Float64', 'LowCardinality(String)',
                'LowCardinality(String)', 'LowCardinality(String)',
                'DateTime64(3, \'UTC\')',
                'DateTime64(3, \'UTC\')'
            ]

            return data, column_names, column_type_names

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