Wassim Kabbani

15 papers B 2Journal 8Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
IEEE Access
Sven Utcke, Sophia Kramp, Sebastian Engelhardt, Wassim Kabbani, Christian Rathgeb, Torsten Schlett, Johannes Merkle, Benjamin Tams, Jonas Dehen, Christoph Busch
2025 J jnl
CoRR
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2025 J jnl
CoRR
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2025 J jnl
CoRR
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2025 J jnl
CoRR
Wassim Kabbani, Tristan Le Pessot, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2025 B conf
IJCB
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2025 J jnl
CoRR
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2024 conf
BIOSIG
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2024 conf
IWBF
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2024 conf
ECCV Workshops (22)
Wassim Kabbani, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2024 B conf
IJCB
Wassim Kabbani, Tristan Le Pessot, Kiran B. Raja, Raghavendra Ramachandra, Christoph Busch
2023 J jnl
CoRR
Wassim Kabbani, Marcel Grimmer, Christoph Busch
2023 conf
BIOSIG
Wassim Kabbani, Christoph Busch, Kiran B. Raja
2023 J jnl
CoRR
Wassim Kabbani, Christoph Busch, Kiran B. Raja
2022 conf
EUVIP
Wassim Kabbani, Marcel Grimmer, Christoph Busch
redb/extractors/decompiler/bninja/similarity/minhasher.py
← Index redb/extractors/decompiler/bninja/similarity/minhasher.py python
import logging
import random
from enum import Enum

from ..analysis.medium_level_normalization import MediumLevelNormalization

try:
    from .minhashcustom import MinHashCustom
    from ..analysis.low_level_normalization import LowLevelNormalization
except ImportError:
    # Fallback to absolute imports (for multiprocessing spawned processes)
    from redb.extractors.decompiler.bninja.similarity.minhashcustom import MinHashCustom
    from redb.extractors.decompiler.bninja.analysis.low_level_normalization import LowLevelNormalization

## Values for this configuration were extracted from https://github.com/danielplohmann/mcrit/blob/main/mcrit/config/MinHashConfig.py#L10
# Length in number of Shingles of which a minhash consists
# this value represents the length of sha256sum hash truncated
MINHASH_SIGNATURE_LENGTH: int = 64
# Number of bits per signature element (1-32 bits)
MINHASH_SIGNATURE_BITS: int = 8


class TokenKind(Enum):
    LLIL = "llil"
    TYPED_LLIL = "typed_llil"
    MLIL = "mlil"
    TYPED_MLIL = "typed_mlil"


class MinHasher:
    # stick to the default method
    MINHASH_STRATEGY_HASH_ALL = 1

    def __init__(self, seed, il_function, kind: TokenKind = TokenKind.LLIL):
        self._minhash_seeds = []
        self.il_func = il_function
        self.kind = kind
        self._minhash_permutation = []
        self._signature_segments = []
        self._initMinhashing(seed)

    def _initMinhashing(self, MINHASH_SEED=None):
        random.seed(MINHASH_SEED)
        # init sequence of seeds
        self._minhash_seeds = [
            random.randint(0, MinHashCustom.getHashMax()) for _ in range(MINHASH_SIGNATURE_LENGTH)
        ]

    def make_ngrams(self, tokens, n=3):
        """Take the ngrams of the IL we try to pass into the functions"""
        return [tuple(tokens[i:i+n]) for i in range(len(tokens) - n + 1)]

    def _extract_tokens(self):
        """Extract the IL tokens from the IL function, picking the right
        normalizer (LLIL/MLIL) and the right normalization mode
        (skeleton/typed) based on self.kind."""
        if self.kind in (TokenKind.LLIL, TokenKind.TYPED_LLIL):
            normalizer = LowLevelNormalization()
        elif self.kind in (TokenKind.MLIL, TokenKind.TYPED_MLIL):
            normalizer = MediumLevelNormalization()
        else:
            raise ValueError(f"Unsupported token kind: {self.kind}")

        # typed variants include operand type info, skeleton variants don't
        if self.kind in (TokenKind.TYPED_LLIL, TokenKind.TYPED_MLIL):
            normalize = normalizer.normalize_instr_with_operands
        else:
            normalize = normalizer.normalize_instruction_all_levels

        instructions = []
        for basic_block in self.il_func.basic_blocks:
            for il in basic_block:
                instructions.append(normalize(il))

        return instructions

    def calculateMinHash(self):
        """Calculate hash function every time, then take minimum shingle per shingler"""
        minhash_result = MinHashCustom(minhash_bits=MINHASH_SIGNATURE_BITS)
        minhash_signature = []

        tokens = self._extract_tokens()
        shingles = self.make_ngrams(tokens, n=3)

        # Functions with fewer than 3 IL instructions can't produce n-grams
        # Return empty minhash for such small functions (thunks, stubs, etc.)
        # Triggered by 39d8ad95b0323c37bd3134ab93ac4af44c66a1a8443a41c1ac02cec19bb2816a
        if not shingles:
            return []

        # Generate the MinHash
        for seed in self._minhash_seeds:
            hashed_shingles = [
                self.shingle_hash(shingle, seed) for shingle in shingles
            ]
            min_value = min(hashed_shingles)

            if MINHASH_SIGNATURE_BITS < 32:
                min_value %= (2 ** MINHASH_SIGNATURE_BITS)

            minhash_signature.append(min_value)

        minhash_result.setMinHash(minhash_signature)
        return minhash_result.getMinHashInt()

    def shingle_hash(self, shingle, hash_seed=0):
        """Produce a single 32bit UINT hash for a given shingle"""
        return MinHashCustom.hashData(shingle, hash_seed)