Han He

52 papers A* 2Misc 1Journal 34Unranked 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
IEEE Trans. Ind. Electron.
Han He, Zhenbin Zhang, Zhen Li, Yuanxiang Sun, Jiateng Gu
2026 J jnl
Frontiers Comput. Neurosci.
Han He, Ruinan Chen, Yixiang Wang, Xia Chen
2025 A* conf
AAAI
Han He, Qianchu Liu, Lei Xu, Chaitanya Shivade, Yi Zhang, Sundararajan Srinivasan, Katrin Kirchhoff
2025 conf
NAACL (Long Papers)
Mahnaz Koupaee, Jake W. Vincent, Saab Mansour, Igor Shalyminov, Han He, Hwanjun Song, Raphael Shu, Jianfeng He, Yi Nian, Amy Wing-mei Wong, Kyu J. Han, Hang Su
2025 J jnl
CoRR
Mahnaz Koupaee, Jake W. Vincent, Saab Mansour, Igor Shalyminov, Han He, Hwanjun Song, Raphael Shu, Jianfeng He, Yi Nian, Amy Wing-mei Wong, Kyu J. Han, Hang Su
2025 J jnl
Health Inf. Sci. Syst.
Hao Ren, Dongxiao Li, Fengshi Jing, Xinyue Zhang, Xingyuan Tian, Songlin Xie, Erfu Zhang, Ruining Wang, Han He, Yinpan He, Yake Xue, Chi Liu, Yu Sun, Weibin Cheng
2025 conf
NAACL (Long Papers)
Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
2025 J jnl
CoRR
Zijie Xu, Minfeng Qi, Shiqing Wu, Lefeng Zhang, Qiwen Wei, Han He, Ningran Li
2024 J jnl
IEEE Trans. Ind. Electron.
Zhenbin Zhang, Junda Li, Zhen Li, Yuanxiang Sun, Han He
2024 conf
DSC
Hao Ren, Zeyu Luo, Fengshi Jing, Xinyue Zhang, Han He, Yonghao Yu, Dawei Zhao
2024 J jnl
CoRR
Han He, Qianchu Liu, Lei Xu, Chaitanya Shivade, Yi Zhang, Sundararajan Srinivasan, Katrin Kirchhoff
2024 J jnl
CoRR
Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
2023 A* conf
AAAI
Han He, Song Feng, Daniele Bonadiman, Yi Zhang, Saab Mansour
2023 J jnl
CoRR
Han He, Jinho D. Choi
2023 J jnl
Trans. Assoc. Comput. Linguistics
Han He, Jinho D. Choi
2023 J jnl
CoRR
Lydia Feng, Gregor Williamson, Han He, Jinho D. Choi
2022 J jnl
J. Medical Syst.
Joshua C. Burton, Samantha Regala, Deonte Williams, Aditi Desai, Han He, Oliver O. Aalami, Edward R. Mariano, Randall S. Stafford, Seshadri C. Mudumbai
2022 J jnl
CoRR
Han He, Song Feng, Daniele Bonadiman, Yi Zhang, Saab Mansour
2022 J jnl
IEEE Trans. Ind. Electron.
Yu Li, Han He, Zhen Li, Zhenbin Zhang
2021 J jnl
CoRR
Sarah E. Finch, James D. Finch, Daniil Huryn, William Hutsell, Xiaoyuan Huang, Han He, Jinho D. Choi
2021 conf
ICCIR
Weijie Deng, Han He, Jinlu Yu, Shuting Zhu
2021 J jnl
CoRR
Han He, Liyan Xu, Jinho D. Choi
2021 conf
UCET
Rujun Song, Chaofan Shi, Haojie Qin, Han He, Zhuoling Xiao
2021 J jnl
CoRR
Han He, Jinho D. Choi
2021 J jnl
IEEE Trans. Circuits Syst. Video Technol.
Yingqiang Qiu, Zhenxing Qian, Han He, Hui Tian, Xinpeng Zhang
2021 J jnl
Comput. Networks
Peng Liu, Han He, Tingting Fu, Huijuan Lu, Abdulhameed Alelaiwi, Md. Wasif Islam Wasi
2021 conf
EMNLP (1)
Han He, Jinho D. Choi
2021 J jnl
CoRR
Han He, Jinho D. Choi
2020 conf
IWPT 2020
Han He, Jinho D. Choi
2020 conf
IWPT 2020
Tae Hwan Oh, Jiyoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, Hansaem Kim
2020 J jnl
CoRR
Tae Hwan Oh, Jiyoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, Hansaem Kim
2020 conf
SeGAH
Adnan Mehmood, Han He, Xiaochen Chen, Aleksi Vianto, Ville Vianto, Johanna Virkki
2020 J jnl
Sensors
Han He, Xiaochen Chen, Adnan Mehmood, Leevi Raivio, Heikki Huttunen, Pasi Raumonen, Johanna Virkki
2020 J jnl
Adv. Hum. Comput. Interact.
Adnan Mehmood, Han He, Xiaochen Chen, Aleksi Vianto, Ville Vianto, Oguz 'Oz' Buruk, Johanna Virkki
2020 conf
SeGAH
Adnan Mehmood, Han He, Xiaochen Chen, Aleksi Vianto, Oguz Turan Buruk, Johanna Virkki
2020 J jnl
J. Intell. Fuzzy Syst.
Han He, Yuanyuan Hong, Weiwei Liu, Sung-A. Kim
2020 Misc conf
FLAIRS
Han He, Jinho D. Choi
2020 J jnl
CoRR
Leevi Raivio, Han He, Johanna Virkki, Heikki Huttunen
2020 J jnl
J. Intell. Fuzzy Syst.
Han He, Si Yi, Weiwei Liu
2020 J jnl
J. Intell. Fuzzy Syst.
Han He, Hongcui Yan, Weiwei Liu
2020 conf
ICSSE
Hsien-Ju Ko, Hao-Cheng Yang, Yuan-bin Wang, Han He
2019 J jnl
Rev. d'Intelligence Artif.
Guoxing Jin, Kai Bai, Yixian Zhang, Han He
2019 conf
RFID-TA
Han He, Xiaochen Chen, Leena Ukkonen, Johanna Virkki
2019 conf
SeGAH
Adnan Mehmood, Shoaib Qureshi, Han He, Xiaochen Chen, Shahbaz Ahmed, Sari Merilampi, Pasi Raumonen, Leena Ukkonen, Johanna Virkki
2019 J jnl
CoRR
Han He, Jinho D. Choi
2019 J jnl
CoRR
Changmao Li, Han He, Yunze Hao, Caleb Ziems
2018 conf
ICACS
Yunxiang Zhang, Xiaokun Yang, Lei Wu, Jiang Lu, Kewei Sha, Archit Gajjar, Han He
2018 conf
RFID-TA
Xiaochen Chen, Han He, Leena Ukkonen, Johanna Virkki, J. Xu, T. Wang, L. Cheng
2018 J jnl
J. Vis. Commun. Image Represent.
Yingqiang Qiu, Han He, Zhenxing Qian, Sheng Li, Xinpeng Zhang
2017 J jnl
CoRR
Han He, Xiaokun Yang, Lei Wu, Hua Yan, Zhimin Gao, Yi Feng, George Townsend
2017 J jnl
CoRR
Han He, Lei Wu, Hua Yan, Zhimin Gao, Yi Feng, George Townsend
2015 J jnl
Int. J. Embed. Syst.
Lu Pu, Xiaowei Xu, Han He, Hanqing Zhou, Zhijun Qiu, Yu Hu
redb/extractors/pe_extractors/pe_extra_findings.py
← Index redb/extractors/pe_extractors/pe_extra_findings.py python
from hashlib import md5, sha1, sha256
import inspect
import pefile
from magika import Magika
import json
from datetime import datetime, timezone
from typing import List, Optional, Any
from asn1crypto import cms, pem, x509, core
from dataclasses import asdict

from redb.extractors.enum import Tag
from redb.extractors.pe_extractor import PEExtractor
from redb.models.dataclasses import PEExtraFinding, PECertificate


class PEExtraFindings(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_extrafindings"
        self.log.debug(inspect.currentframe().f_code.co_name)
        self.has_binary_overlay = False
        self.has_binary_resource = False
        self.findings = []

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

    """
    The section below triggers in case of a binary which is not signed.
    It trigger the scan for Certificates inside the binary, for example
    inside a resource or an overlay.
    """

    def _scan_for_certificates(self):
        """
        Comprehensive scan for certificate data in PE file.
        Returns list of tuples (location_description, certificate_data)
        """
        self.log.debug(inspect.currentframe().f_code.co_name)

        # 1. Scan resources for embedded PE files
        self._scan_resources_for_certificates()

        # 3. Scan overlay
        overlay_data = self.pe.get_overlay()
        if overlay_data:
            self._scan_overlay_for_certificates(overlay_data)


    def _extract_certificate_info(self, cert_data):
        self.log.debug(inspect.currentframe().f_code.co_name)

        certificate = x509.Certificate.load(cert_data)
        certificate_serial_number = format(certificate.serial_number, "x").upper()
        grouped_serial_number = ":".join(
            [
                certificate_serial_number[i : i + 2]
                for i in range(0, len(certificate_serial_number), 2)
            ]
        )
        return PECertificate(
            certificate_serial_number=grouped_serial_number,
            certificate_issuer=certificate.issuer.human_friendly,
            certificate_subject=certificate.subject.human_friendly,
            certificate_valid_from=certificate["tbs_certificate"]["validity"][
                "not_before"
            ].native.strftime("%Y-%m-%d %H:%M:%S"),
            certificate_valid_to=certificate["tbs_certificate"]["validity"][
                "not_after"
            ].native.strftime("%Y-%m-%d %H:%M:%S"),
            certificate_thumbprint=sha1(cert_data).hexdigest().upper(),
            certificate_algorithm=None,
        )

    def _extract_standard_certificates(self, pe):
        self.log.debug(inspect.currentframe().f_code.co_name)
        address = pe.OPTIONAL_HEADER.DATA_DIRECTORY[
            pefile.DIRECTORY_ENTRY["IMAGE_DIRECTORY_ENTRY_SECURITY"]
        ].VirtualAddress
        size = pe.OPTIONAL_HEADER.DATA_DIRECTORY[
            pefile.DIRECTORY_ENTRY["IMAGE_DIRECTORY_ENTRY_SECURITY"]
        ].Size

        addr_8 = address + 8
        signature_data = bytes(
            pe.write()[addr_8 : addr_8 + size]  # noqa E203
        )  # Ensure this is a bytes object
        if pem.detect(signature_data):
            signature_data = pem.unarmor(signature_data)

        content_info = cms.ContentInfo.load(signature_data)
        signed_data = content_info["content"]
        certificates = signed_data["certificates"]

        certificates_list = []
        for cert in certificates:
            cert_info = self._extract_certificate_info(cert.chosen.dump())
            certificates_list.append(cert_info)

        return certificates_list

    def _is_signed(self, pedata):
        address = pedata.OPTIONAL_HEADER.DATA_DIRECTORY[
            pefile.DIRECTORY_ENTRY["IMAGE_DIRECTORY_ENTRY_SECURITY"]
        ].VirtualAddress
        if address == 0:
            return False
        return True

    def _scan_resources_for_certificates(self):
        """Scan resources for embedded PE files and their certificates"""
        self.log.debug(inspect.currentframe().f_code.co_name)

        try:
            if hasattr(self.pe, "DIRECTORY_ENTRY_RESOURCE"):
                for entry in self.pe.DIRECTORY_ENTRY_RESOURCE.entries:
                    for resource in self._get_resource_data(entry):
                        # Check if resource data might be a PE file
                        resource_magika = Magika().identify_bytes(resource).output.label
                        if resource.startswith(b"MZ") or resource_magika == "pebin":
                            try:
                                embedded_pe = pefile.PE(data=resource)
                                if self._is_signed(embedded_pe):
                                    cert_data = self._extract_standard_certificates(
                                        embedded_pe
                                    )
                                    if cert_data:
                                        # certificates.append(
                                        #     (f"Resource_{entry.id}", cert_data)
                                        # )
                                        self.findings.append(
                                            PEExtraFinding(
                                                context=f"Resource ({sha256(resource).hexdigest()}) is a PE file. Found Code Signing Certificates information inside.",
                                                finding=cert_data,
                                            )
                                        )
                            except Exception as e:
                                self.log.warning(
                                    f"Resource {sha256(resource).hexdigest()} is not a valid PE: {e}"
                                )

                        # Direct certificate pattern matching in resource
                        cert_data = self._find_certificate_patterns(resource)
                        if cert_data:
                            # certificates.append((f"Resource_{entry.id}", cert_data))
                            self.findings.append(
                                PEExtraFinding(
                                    context=f"Resource ({sha256(resource).hexdigest()}) is a PE file.\
                                    Found Code Signing Certificates information inside.",
                                    finding=cert_data,
                                )
                            )

        except Exception as e:
            self.log.error(f"Failed to scan resources: {e}")


    def _scan_overlay_for_certificates(self, overlay_data) -> List[bytes]:
        """Scan PE overlay for certificate data"""
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            # Check if overlay is a PE file
            overlay_magika = Magika().identify_bytes(overlay_data).output.ct_label
            if overlay_data.startswith(b"MZ") or overlay_magika == "pebin":
                try:
                    overlay_pe = pefile.PE(data=overlay_data)
                    if self._is_signed(overlay_pe):
                        cert_data = self._extract_standard_certificates(overlay_data)
                        if cert_data:
                            self.findings.append(
                                PEExtraFinding(
                                    context=f"Overlay data ({sha256(overlay_data).hexdigest()}) is a PE file.\
                                    Found Code Signing Certificates information inside.",
                                    finding=cert_data,
                                )
                            )
                except Exception as e:
                    self.log.warning(f"Error looking for certificates in Overlay: {e}")
                    pass

            # Direct certificate pattern matching in overlay
            cert_data = self._find_certificate_patterns(overlay_data)
            if cert_data:
                self.findings.append(
                    PEExtraFinding(
                        context=f"Overlay data ({sha256(overlay_data).hexdigest()}) is a PE file.\
                        Found Code Signing Certificates information inside.",
                        finding=cert_data,
                    )
                )
        except Exception as e:
            self.log.error(f"Failed to scan overlay: {e}")


    def _get_resource_data(self, entry) -> List[bytes]:
        """Recursively get resource data"""
        resources = []
        try:
            if hasattr(entry, "directory"):
                for subentry in entry.directory.entries:
                    resources.extend(self._get_resource_data(subentry))
            else:
                data = self.pe.get_data(
                    entry.data.struct.OffsetToData, entry.data.struct.Size
                )
                resources.append(data)
        except Exception as e:
            self.log.error(f"Failed to get resource data: {e}")
        return resources

    def _find_certificate_patterns(self, data: bytes) -> Optional[bytes]:
        """Find certificate patterns in binary data"""
        # PKCS#7 SignedData OID pattern
        PKCS7_PATTERN = b"\x06\x09\x2A\x86\x48\x86\xF7\x0D\x01\x07\x02"

        try:
            idx = data.find(PKCS7_PATTERN)
            if idx != -1:
                # Search backwards for ASN.1 sequence marker
                for i in range(idx, max(0, idx - 50), -1):
                    if data[i] == 0x30:  # ASN.1 SEQUENCE
                        try:
                            # Try to parse as X.509 certificate
                            cert = x509.load_der_x509_certificate(
                                data[i:], default_backend()
                            )
                            return data[i:]
                        except Exception:
                            continue
        except Exception as e:
            self.log.error(f"Failed to find certificate patterns: {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.findings
        elif exporter_type == "ClickHouseExporter":
            current_time = datetime.now(timezone.utc)
            
            data = [
                [
                    self.sha256,
                    self.md5,
                    self.sha1,
                    finding.context,
                    [asdict(cert) for cert in finding.finding] if finding.finding else None,
                    current_time
                ]
                for finding in self.findings
            ]
            
            column_names = [
                'sha256', 'md5', 'sha1', 'context', 'finding', 'analysis_date'
            ]
            
            if not data:
                return None

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

            return (data, column_names, column_type_names)

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

    def extract(self):
        try:
            self.log.debug(inspect.currentframe().f_code.co_name)
            self._scan_for_certificates()
            if len(self.findings) > 0:
                return self.findings
            return None
        except Exception as e:
            self.log.error(f"Error extracting PE Extras: {e}")
            return None