Rajendra D. Kanphade

13 papers Journal 6Unranked 7
YearRankTypeTitle / Venue / Authors
2023 J jnl
Vis. Comput.
Pallavi V. Mulmule, Rajendra D. Kanphade, Dhiraj Manohar Dhane
2022 J jnl
Concurr. Comput. Pract. Exp.
Gayatri Umakant Bokade, Rajendra D. Kanphade
2022 J jnl
Int. J. Medical Eng. Informatics
Pallavi V. Mulmule, Rajendra D. Kanphade
2022 J jnl
Int. J. Biom.
Gayatri Umakant Bokade, Rajendra D. Kanphade
2021 J jnl
Int. J. Comput. Vis. Robotics
Gayatri Umakant Bokade, Rajendra D. Kanphade
2020 J jnl
IEEE Access
Sagar V. Joshi, Rajendra D. Kanphade
2019 conf
ICCCNT
Gayatri Umakant Bokade, Rajendra D. Kanphade
2018 conf
ISDA (2)
Sagar V. Joshi, Rajendra D. Kanphade
2014 conf
ICACCI
Navnath S. Narawade, Rajendra D. Kanphade
2011 conf
ICWET
Rajendra D. Kanphade, S. B. Patil, A. M. Patokar, D. D. Nawgaje
2011 conf
ICWET
D. D. Nawgaje, Rajendra D. Kanphade
2010 conf
ICWET
Manoj Sankhe, Rajendra D. Kanphade
2010 conf
ICWET
M. U. Nemade, Rajendra D. Kanphade
redb/extractors/decompiler/bninja/analysis/medium_level.py
← Index redb/extractors/decompiler/bninja/analysis/medium_level.py python
import time

from binaryninja import (
    MediumLevelILOperation as MLIL_OP,
)

try:
    from ..function_type import FunctionTypeAnalysis
    from ..similarity.minhasher import MinHasher, TokenKind
    from ..utils.hashes import calculate_sha256, calculate_tlsh
    from .medium_level_normalization import MediumLevelNormalization
except ImportError:
    from redb.extractors.decompiler.bninja.analysis.medium_level_normalization import MediumLevelNormalization
    from redb.extractors.decompiler.bninja.similarity.minhasher import MinHasher
    from redb.extractors.decompiler.bninja.function_type import FunctionTypeAnalysis
    from redb.extractors.decompiler.bninja.utils.hashes import calculate_sha256, calculate_tlsh


_MLIL_CALL_OPS = (
    MLIL_OP.MLIL_CALL,
    MLIL_OP.MLIL_CALL_SSA,
    MLIL_OP.MLIL_CALL_UNTYPED,
    MLIL_OP.MLIL_CALL_UNTYPED_SSA,
    MLIL_OP.MLIL_TAILCALL,
    MLIL_OP.MLIL_TAILCALL_SSA,
    MLIL_OP.MLIL_TAILCALL_UNTYPED,
    MLIL_OP.MLIL_TAILCALL_UNTYPED_SSA,
)

_MLIL_CONTROL_FLOW_OPS = (
    MLIL_OP.MLIL_IF,
    MLIL_OP.MLIL_GOTO,
    MLIL_OP.MLIL_JUMP,
    MLIL_OP.MLIL_JUMP_TO,
    MLIL_OP.MLIL_RET,
    MLIL_OP.MLIL_RET_HINT,
    MLIL_OP.MLIL_NORET,
) + _MLIL_CALL_OPS


class MediumLevelAnalysis:
    def __init__(self, function, bv, logger):
        self.function = function
        self.name = function.name
        self.start = function.start
        self.mlil_func = function.mlil
        self.bv = bv
        self.logger = logger
        self.errors = []

    def log_error(self, message, function_name, address, exception=None, error_location="unknown"):
        error_msg = f"Error in function {function_name} at {address}: {message}"
        if exception:
            error_msg += f" - {str(exception)}"
        self.logger.error(error_msg)

        error = {
            "function_name": function_name,
            "function_address": str(address),
            "error_location": error_location,
            "error_message": message,
            "error_details": str(exception) if exception else "",
            "error_type": type(exception).__name__ if exception else "Unknown",
            "timestamp": int(time.time() * 1000),
        }
        self.errors.append(error)

    def _collect_mlil_skeleton_and_typed(self):
        mlil = self.mlil_func
        if not mlil:
            return [], [], [], []

        start = self.start
        norm = MediumLevelNormalization()

        skeleton = []
        skeleton_with_addr = []
        typed = []
        typed_with_addr = []

        for il in mlil.instructions:
            skel_norm = norm.normalize_instruction_all_levels(il)
            typed_norm = norm.normalize_instr_with_operands(il)

            skeleton.append(skel_norm)
            typed.append(typed_norm)

            offset = il.address - start
            if offset < 0:
                offset = 0

            skeleton_with_addr.append((offset, skel_norm))
            typed_with_addr.append((offset, typed_norm))

        return skeleton, skeleton_with_addr, typed, typed_with_addr

    def analyze(self):
        (
            instr_skeleton,
            body_mlil_skeleton_vector,
            instr_typed,
            body_mlil_typed_vector,
        ) = self._collect_mlil_skeleton_and_typed()

        instr_skeleton_str = str(instr_skeleton)
        sha256_skeleton = calculate_sha256(instr_skeleton_str)
        tlsh_skeleton = calculate_tlsh(instr_skeleton_str)

        instr_typed_str = str(instr_typed)
        sha256_typed = calculate_sha256(instr_typed_str)
        tlsh_typed = calculate_tlsh(instr_typed_str)

        seed = 0xdeadbeef
        minhash_mlil_skeleton = MinHasher(seed, self.mlil_func, TokenKind.MLIL).calculateMinHash()
        minhash_mlil_typed = MinHasher(seed, self.mlil_func, TokenKind.TYPED_MLIL).calculateMinHash()

        medium_level_json = {
            "function_address": self.start,
            "body_mlil_skeleton_vector": body_mlil_skeleton_vector,
            "sha256_mlil_skeleton": sha256_skeleton,
            "tlsh_mlil_skeleton": tlsh_skeleton,
            "minhash_mlil_skeleton": minhash_mlil_skeleton,
            "body_mlil_typed_vector": body_mlil_typed_vector,
            "sha256_mlil_typed": sha256_typed,
            "tlsh_mlil_typed": tlsh_typed,
            "minhash_mlil_typed": minhash_mlil_typed,
        }

        return medium_level_json, self.errors