Kaan Kara

31 papers A* 1A 2B 4Misc 2Journal 18Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Netw. Model. Anal. Health Informatics Bioinform.
Kaan Kara, Öyküm Esra Yigit, Tuba Gunel
2025 J jnl
J. Medical Syst.
Kaan Kara, Tuba Gunel
2024 J jnl
VLDB J.
Lijie Xu, Shuang Qiu, Binhang Yuan, Jiawei Jiang, Cédric Renggli, Shaoduo Gan, Kaan Kara, Guoliang Li, Ji Liu, Wentao Wu, Jieping Ye, Ce Zhang
2022 J jnl
ACM Trans. Reconfigurable Technol. Syst.
Runbin Shi, Kaan Kara, Christoph Hagleitner, Dionysios Diamantopoulos, Dimitris Syrivelis, Gustavo Alonso
2022 conf
SIGMOD Conference
Lijie Xu, Shuang Qiu, Binhang Yuan, Jiawei Jiang, Cédric Renggli, Shaoduo Gan, Kaan Kara, Guoliang Li, Ji Liu, Wentao Wu, Jieping Ye, Ce Zhang
2022 J jnl
CoRR
Lijie Xu, Shuang Qiu, Binhang Yuan, Jiawei Jiang, Cédric Renggli, Shaoduo Gan, Kaan Kara, Guoliang Li, Ji Liu, Wentao Wu, Jieping Ye, Ce Zhang
2020 J jnl
IEEE Trans. Signal Process.
Nezihe Merve Gürel, Kaan Kara, Alen Stojanov, Tyler M. Smith, Thomas Lemmin, Dan Alistarh, Markus Püschel, Ce Zhang
2020 J jnl
Found. Trends Databases
Zsolt István, Kaan Kara, David Sidler
2020 B conf
FPL
Kaan Kara, Christoph Hagleitner, Dionysios Diamantopoulos, Dimitris Syrivelis, Gustavo Alonso
2020 J jnl
CoRR
Kaan Kara, Christoph Hagleitner, Dionysios Diamantopoulos, Dimitris Syrivelis, Gustavo Alonso
2020 B conf
FPL
Amit Kulkarni, Monica Chiosa, Thomas B. Preußer, Kaan Kara, David Sidler, Gustavo Alonso
2020 J jnl
CoRR
Amit Kulkarni, Monica Chiosa, Thomas B. Preußer, Kaan Kara, David Sidler, Gustavo Alonso
2020 J jnl
ACM Trans. Reconfigurable Technol. Syst.
Kaan Kara, Gustavo Alonso
2020
Kaan Kara
2020 A conf
CIDR
Gustavo Alonso, Timothy Roscoe, David A. Cock, Mohsen Ewaida, Kaan Kara, Dario Korolija, David Sidler, Zeke Wang
2019 J jnl
CoRR
Zeke Wang, Kaan Kara, Hantian Zhang, Gustavo Alonso, Onur Mutlu, Ce Zhang
2019 J jnl
Proc. VLDB Endow.
Zeke Wang, Kaan Kara, Hantian Zhang, Gustavo Alonso, Ce Zhang, Onur Mutlu
2019 J jnl
IEEE Data Eng. Bull.
Gustavo Alonso, Zsolt István, Kaan Kara, Muhsen Owaida, David Sidler
2019 J jnl
Proc. VLDB Endow.
Kaan Kara, Zeke Wang, Ce Zhang, Gustavo Alonso
2018 J jnl
Proc. VLDB Endow.
Kaan Kara, Ken Eguro, Ce Zhang, Gustavo Alonso
2018 J jnl
CoRR
Nezihe Merve Gürel, Kaan Kara, Dan Alistarh, Ce Zhang
2018 A conf
AISTATS
Heng Guo, Kaan Kara, Ce Zhang
2017 Misc conf
FCCM
Muhsen Owaida, David Sidler, Kaan Kara, Gustavo Alonso
2017 Misc conf
FCCM
Kaan Kara, Dan Alistarh, Gustavo Alonso, Onur Mutlu, Ce Zhang
2017 conf
SIGMOD Conference
Kaan Kara, Jana Giceva, Gustavo Alonso
2017 J jnl
CoRR
Heng Guo, Kaan Kara, Ce Zhang
2017 A* conf
ICML
Hantian Zhang, Jerry Li, Kaan Kara, Dan Alistarh, Ji Liu, Ce Zhang
2017 conf
SIGMOD Conference
David Sidler, Zsolt István, Muhsen Owaida, Kaan Kara, Gustavo Alonso
2017 B conf
FPL
David Sidler, Muhsen Owaida, Zsolt István, Kaan Kara, Gustavo Alonso
2016 B conf
FPL
Kaan Kara, Gustavo Alonso
2016 J jnl
CoRR
Hantian Zhang, Kaan Kara, Jerry Li, Dan Alistarh, Ji Liu, Ce Zhang
redb/extractors/pe_extractors/pe_sections.py
← Index redb/extractors/pe_extractors/pe_sections.py python
import base64
import hashlib
import inspect
from redb.extractors.enum import Tag
from redb.extractors.pe_extractor import PEExtractor
from redb.models.dataclasses import PESection
from datetime import datetime, timezone
from typing import Any


class PESectionExtractor(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_sections"
        self.log.debug(inspect.currentframe().f_code.co_name)

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

    def _extract_sections(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        sections = []
        for section in self.pe.sections:
            try:
                name = self.process_binary_string(section.Name)
            except Exception as e:
                name = "UnableToDecode"
                self.log.warning(
                    f'Unable to store section Name "{section.Name}" for {self.hash.sha256}'
                    f" exception {e}"
                )
            sec_sha256 = section.get_hash_sha256()
            sec_md5 = section.get_hash_md5()
            # sec_entropy = "%.2f" % section.get_entropy()
            sec_entropy = section.get_entropy()
            pe_section = PESection(
                _id=hashlib.sha256(
                    name.encode()
                ).hexdigest(),  # usecase 8e035beb02a411f8a9e92d4cf184ad34f52bbd0a81a50c222cdd4706e4e45104, all section have same sha256
                section_name=name,
                section_name_b64=base64.b64encode(
                    section.Name.rstrip(b'\x00')
                ).decode(),  # base64.b64decode(b64) to decode
                section_v_addr=section.VirtualAddress,
                section_v_addr_hex=hex(section.VirtualAddress),
                section_v_size=section.Misc_VirtualSize,
                section_size=section.SizeOfRawData,
                section_pointer_to_raw_data=hex(section.PointerToRawData),
                section_md5=sec_md5,
                section_sha256=sec_sha256,
                section_entropy=sec_entropy,
            )
            sections.append(pe_section)
        return sections

    def extract(self):
        self.log.debug(inspect.currentframe().f_code.co_name)
        try:
            sections = self._extract_sections()
            # self.export_to_elastic(sections)  # Let the exporters handle this
            return sections
        except Exception as e:
            self.log.error(f"Error extracting PE sections: {e}")
            return None

    def prepare_export_data(self, exporter_type: str) -> Any:
        if exporter_type == "ElasticsearchExporter":
            return self.extract()
        elif exporter_type == "ClickHouseExporter":
            sections = self.extract()
            if sections is None:
                return None
            
            data = []
            current_time = datetime.now(timezone.utc)
            
            for section in sections:
                data.append([
                    self.sha256,                          # sha256
                    self.md5,                             # md5
                    self.sha1,                            # sha1
                    section.section_name,                 # section_name
                    section.section_name_b64,             # section_name_b64
                    section.section_entropy,              # section_entropy
                    section.section_sha256,               # section_sha256
                    section.section_md5,                  # section_md5
                    section.section_size,                 # section_size
                    section.section_v_addr,               # section_v_addr
                    section.section_v_size,               # section_v_size
                    int(section.section_pointer_to_raw_data, 16),  # section_pointer_to_raw_data - convert from hex
                    current_time                          # analysis_date
                ])
            
            column_names = [
                'sha256', 'md5', 'sha1', 'section_name', 'section_name_b64',
                'section_entropy', 'section_sha256', 'section_md5', 'section_size',
                'section_v_addr', 'section_v_size', 'section_pointer_to_raw_data',
                'analysis_date'
            ]
            
            if not data:
                return None

            column_type_names = [
                'FixedString(64)', 'FixedString(32)', 'FixedString(40)',
                'LowCardinality(String)', 'LowCardinality(String)',
                'Float64', 'FixedString(64)', 'FixedString(32)', 'UInt64',
                'UInt64', 'UInt64', 'UInt64',
                'DateTime64(3, \'UTC\')'
            ]

            return (data, column_names, column_type_names)

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