N. R. Achuthan

25 papers B 1C 1Journal 18Unranked 4
YearRankTypeTitle / Venue / Authors
2013 conf
ICEIS
Amit Rudra, Raj P. Gopalan, N. R. Achuthan
2013 conf
ICEIS (1)
Amit Rudra, Raj P. Gopalan, N. R. Achuthan
2011 J jnl
Discret. Math.
Nirmala Achuthan, N. R. Achuthan, Mudin Simanihuruk
2011 J jnl
Australas. J Comb.
Nirmala Achuthan, N. R. Achuthan, Mudin Simanihuruk
2009 J jnl
Asia Pac. J. Oper. Res.
B. Ramaseshan, N. R. Achuthan, Roger Collinson
2008 J jnl
Int. J. Inf. Technol. Decis. Mak.
B. Ramaseshan, N. R. Achuthan, Roger Collinson
2008 B conf
PAKDD
Alva Erwin, Raj P. Gopalan, N. R. Achuthan
2007 conf
AIDM
Alva Erwin, Raj P. Gopalan, N. R. Achuthan
2007 C conf
CIT
Alva Erwin, Raj P. Gopalan, N. R. Achuthan
2006 ch.
Selected Papers from AusDM
N. R. Achuthan, Raj P. Gopalan, Amit Rudra
2003 J jnl
Transp. Sci.
N. R. Achuthan, Lou Caccetta, Stephen P. Hill
2003 J jnl
Electron. Notes Discret. Math.
Nirmala Achuthan, N. R. Achuthan, Mudin Simanihuruk
2003 J jnl
Electron. Notes Discret. Math.
N. R. Achuthan
2001 J jnl
Ann. Oper. Res.
N. R. Achuthan, A. Hardjawidjaja
1999 J jnl
Australas. J Comb.
Nirmala Achuthan, N. R. Achuthan, Lou Caccetta
1997 J jnl
Australas. J Comb.
Mudin Simanihuruk, Nirmala Achuthan, N. R. Achuthan
1997 J jnl
Australas. J Comb.
Mudin Simanihuruk, Nirmala Achuthan, N. R. Achuthan
1997 conf
ISPAN
Kai Kwong Lau, Mohan J. Kumar, N. R. Achuthan
1996 J jnl
Australas. J Comb.
Nirmala Achuthan, N. R. Achuthan, Mudin Simanihuruk
1996 J jnl
Discret. Math.
Nirmala Achuthan, N. R. Achuthan, Lou Caccetta
1994 J jnl
Australas. J Comb.
N. R. Achuthan, Lou Caccetta, P. Caccetta, James F. Geelen
1993 J jnl
Australas. J Comb.
N. R. Achuthan, Lou Caccetta
1992 J jnl
Australas. J Comb.
N. R. Achuthan, Lou Caccetta
1990 J jnl
Australas. J Comb.
N. R. Achuthan, Mudin Simanihuruk
1990 J jnl
Australas. J Comb.
Nirmala Achuthan, N. R. Achuthan, Lou Caccetta
redb/extractors/elf_extractors/elf_segments.py
← Index redb/extractors/elf_extractors/elf_segments.py python
import inspect
import hashlib
import math
from collections import Counter
from datetime import datetime, timezone
from typing import Any, List, Dict

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 ELFSegment


class ELFSegmentExtractor(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_segments = []
        self.elastic_index = self.index_prefix + "-elf_segments"
        self.log.debug(inspect.currentframe().f_code.co_name)

    def _is_empty_result(self, extracted_data) -> bool:
        """
        Override: Empty segments is an ERROR, not a valid empty case.
        A valid ELF file must have segments (program headers).
        """
        # Always return False - empty segments should be treated as an error
        return False

    def _calculate_entropy(self, data: bytes) -> float:
        """Calculate Shannon entropy of data."""
        if not data:
            return 0.0

        try:
            # Count frequency of each byte
            byte_counts = Counter(data)
            data_len = len(data)

            # Calculate entropy
            entropy = 0.0
            for count in byte_counts.values():
                if count > 0:
                    frequency = count / data_len
                    entropy -= frequency * math.log2(frequency)

            return entropy
        except Exception as e:
            self.log.error(f"Error calculating entropy: {e}")
            return 0.0

    def _map_segment_type(self, p_type_str: str) -> int:
        """Map segment type string to enum value."""
        type_map = {
            'PT_NULL': 0,
            'PT_LOAD': 1,
            'PT_DYNAMIC': 2,
            'PT_INTERP': 3,
            'PT_NOTE': 4,
            'PT_SHLIB': 5,
            'PT_PHDR': 6,
            'PT_TLS': 7
        }
        return type_map.get(p_type_str, 0)

    def _decode_segment_flags(self, flags: int) -> List[str]:
        """Decode segment flags to human-readable strings."""
        flag_strings = []

        if flags & 0x1:  # PF_X
            flag_strings.append('EXECUTE')
        if flags & 0x2:  # PF_W
            flag_strings.append('WRITE')
        if flags & 0x4:  # PF_R
            flag_strings.append('READ')

        return flag_strings if flag_strings else ['NONE']

    def _extract_segment_data(self, segment) -> ELFSegment:
        """Extract data from a single segment with granular error handling."""
        # Initialize with safe defaults
        segment_type = 0
        segment_type_str = 'unknown'
        segment_flags = 0
        segment_flags_str = ['NONE']
        segment_offset = 0
        segment_vaddr = 0
        segment_paddr = 0
        segment_filesz = 0
        segment_memsz = 0
        segment_align = 0
        segment_entropy = 0.0
        segment_sha256 = ""
        segment_md5 = ""

        # Try to get segment header
        header = None
        try:
            header = segment.header
        except Exception as e:
            self.log.warning(f"Could not access segment header: {e}")
            return ELFSegment(
                segment_type=segment_type, segment_type_str=segment_type_str,
                segment_flags=segment_flags, segment_flags_str=segment_flags_str,
                segment_offset=segment_offset, segment_vaddr=segment_vaddr,
                segment_paddr=segment_paddr, segment_filesz=segment_filesz,
                segment_memsz=segment_memsz, segment_align=segment_align,
                segment_entropy=segment_entropy, segment_sha256=segment_sha256,
                segment_md5=segment_md5
            )

        # Extract segment type
        try:
            p_type_str = header.get('p_type', 'PT_NULL')
            segment_type = self._map_segment_type(p_type_str)
            segment_type_str = p_type_str.replace('PT_', '') if p_type_str.startswith('PT_') else p_type_str
        except Exception as e:
            self.log.warning(f"Could not extract segment type: {e}")

        # Extract segment flags
        try:
            segment_flags = header.get('p_flags', 0)
            segment_flags_str = self._decode_segment_flags(segment_flags)
        except Exception as e:
            self.log.warning(f"Could not extract segment flags: {e}")

        # Extract segment addresses and sizes
        try:
            segment_offset = header.get('p_offset', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment offset: {e}")

        try:
            segment_vaddr = header.get('p_vaddr', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment vaddr: {e}")

        try:
            segment_paddr = header.get('p_paddr', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment paddr: {e}")

        try:
            segment_filesz = header.get('p_filesz', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment filesz: {e}")

        try:
            segment_memsz = header.get('p_memsz', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment memsz: {e}")

        try:
            segment_align = header.get('p_align', 0)
        except Exception as e:
            self.log.warning(f"Could not extract segment align: {e}")

        # Calculate entropy and hashes for segment data (most likely to fail)
        try:
            if segment_filesz > 0:
                segment_data = segment.data()
                if segment_data:
                    # Calculate entropy
                    segment_entropy = self._calculate_entropy(segment_data)

                    # Calculate hashes
                    segment_sha256 = hashlib.sha256(segment_data).hexdigest()
                    segment_md5 = hashlib.md5(segment_data).hexdigest()
        except Exception as e:
            self.log.warning(f"Could not read segment data for hashing: {e}")
            # Keep defaults (0.0, "", "")

        return ELFSegment(
            segment_type=segment_type,
            segment_type_str=segment_type_str,
            segment_flags=segment_flags,
            segment_flags_str=segment_flags_str,
            segment_offset=segment_offset,
            segment_vaddr=segment_vaddr,
            segment_paddr=segment_paddr,
            segment_filesz=segment_filesz,
            segment_memsz=segment_memsz,
            segment_align=segment_align,
            segment_entropy=segment_entropy,
            segment_sha256=segment_sha256,
            segment_md5=segment_md5
        )

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

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

            def extract_segments(elf):
                segments_data = []

                # Iterate through all segments with per-segment error handling
                for segment_index, segment in enumerate(elf.iter_segments()):
                    try:
                        segment_data = self._extract_segment_data(segment)
                        if segment_data:
                            segments_data.append(segment_data)
                        else:
                            self.log.warning(f"Failed to extract data for segment {segment_index}")
                    except Exception as e:
                        self.log.warning(f"Error processing segment {segment_index}: {e}")
                        # Continue processing other segments

                return segments_data

            # Check if file is valid ELF
            if not self._is_elf_file():
                self.log.error(f"No valid ELF file for {self.hash.sha256}")
                return None

            segments_data = self._with_elf_file(extract_segments)
            if segments_data is None:
                return None

            self.elf_segments = segments_data
            return self.elf_segments

        except Exception as e:
            self.log.error(f"Error extracting ELF segments {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_segments
        elif exporter_type == "ClickHouseExporter":
            try:
                if not self.elf_segments:
                    return None

                # Prepare data arrays for all segments
                data = []
                current_time = datetime.now(timezone.utc)
                for segment in self.elf_segments:
                    row = [
                        self.sha256,
                        self.md5,
                        self.sha1,
                        segment.segment_type,
                        segment.segment_type_str,
                        segment.segment_flags,
                        segment.segment_flags_str,
                        segment.segment_offset,
                        segment.segment_vaddr,
                        segment.segment_paddr,
                        segment.segment_filesz,
                        segment.segment_memsz,
                        segment.segment_align,
                        segment.segment_entropy,
                        segment.segment_sha256,
                        segment.segment_md5,
                        current_time
                    ]
                    data.append(row)

                column_names = [
                    'sha256', 'md5', 'sha1',
                    'segment_type', 'segment_type_str', 'segment_flags', 'segment_flags_str',
                    'segment_offset', 'segment_vaddr', 'segment_paddr',
                    'segment_filesz', 'segment_memsz', 'segment_align',
                    'segment_entropy', 'segment_sha256', 'segment_md5',
                    'analysis_date'
                ]

                column_type_names = [
                    'FixedString(64)', 'FixedString(32)', 'FixedString(40)',
                    "Enum8('NULL'=0, 'LOAD'=1, 'DYNAMIC'=2, 'INTERP'=3, 'NOTE'=4, 'SHLIB'=5, 'PHDR'=6, 'TLS'=7)",
                    'LowCardinality(String)',
                    'UInt32',
                    'Array(LowCardinality(String))',
                    'UInt64', 'UInt64', 'UInt64', 'UInt64', 'UInt64', 'UInt64',
                    'Float64',
                    'FixedString(64)', 'FixedString(32)',
                    '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_segments"