Nathan Wycoff

28 papers A* 1A 1Journal 22Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
J. Glob. Optim.
Nathan Wycoff, John W. Smith, Annie S. Booth, Robert B. Gramacy
2025 J jnl
CoRR
Simon Segert, Nathan Wycoff
2025 J jnl
CoRR
Poorbita Kundu, Nathan Wycoff
2025 J jnl
CoRR
Nathan Wycoff, Ali Arab, Lisa Singh
2025 J jnl
CoRR
Nathan Wycoff
2025 J jnl
EPJ Data Sci.
Helge Marahrens, Ameeta Agrawal, Ali Arab, Katharine M. Donato, Yaguang Liu, Nathan Wycoff, Mohamed Ahmed, Colin Hwang, Lina Laghzaoui, Kate Liggio, Bernardo Medeiros, Jenny Park, Rich Pihlstrom, Eliza Salamon, Mattea Whitlow, Lisa Singh
2024 J jnl
CoRR
Nathan Wycoff, Lisa Singh, Ali Arab, Katharine M. Donato
2024 J jnl
CoRR
Nathan Wycoff
2024 A conf
AISTATS
Nathan Wycoff
2024 J jnl
J. Comput. Soc. Sci.
Nathan Wycoff, Lisa Singh, Ali Arab, Katharine M. Donato, Helge Marahrens
2024 J jnl
CoRR
Nathan Wycoff, John W. Smith, Annie S. Booth, Robert B. Gramacy
2023 J jnl
CoRR
Nathan Wycoff
2022 J jnl
ACM Trans. Evol. Learn. Optim.
Mickaël Binois, Nathan Wycoff
2022 J jnl
Technometrics
Nathan Wycoff, Mickaël Binois, Robert B. Gramacy
2022 A* conf
NeurIPS
Robert B. Gramacy, Annie Sauer, Nathan Wycoff
2021
Nathan Wycoff
2021 conf
ICONS
Zixuan Zhao, Nathan Wycoff, Neil Getty, Rick Stevens, Fangfang Xia
2021 J jnl
CoRR
Zixuan Zhao, Nathan Wycoff, Neil Getty, Rick Stevens, Fangfang Xia
2021 J jnl
CoRR
Nathan Wycoff, Mickaël Binois, Robert B. Gramacy
2021 J jnl
J. Comput. Graph. Stat.
Nathan Wycoff, Mickaël Binois, Stefan M. Wild
2021 J jnl
CoRR
Robert B. Gramacy, Annie Sauer, Nathan Wycoff
2020 J jnl
CoRR
Nathan Wycoff, Prasanna Balaprakash, Fangfang Xia
2019 J jnl
Big Data Res.
Michelle Dowling, Nathan Wycoff, Brian Mayer, John E. Wenskovitch, Scotland Leman, Leanna House, Nicholas F. Polys, Chris North, Peter Hauck
2019 conf
ICONS
Nathan Wycoff, Prasanna Balaprakash, Fangfang Xia
2019 J jnl
CoRR
Nathan Wycoff, Prasanna Balaprakash, Fangfang Xia
2019 J jnl
CoRR
Nathan Wycoff, Mickaël Binois, Stefan M. Wild
2018 J jnl
IEEE Trans. Learn. Technol.
Xin Chen, Jessica Zeitz Self, Leanna House, John E. Wenskovitch, Maoyuan Sun, Nathan Wycoff, Jane Robertson Evia, Scotland Leman, Chris North
2015 conf
BDVA
Lauren Bradel, Nathan Wycoff, Leanna House, Chris North
redb/extractors/decompiler/apk/analyzer.py
← Index redb/extractors/decompiler/apk/analyzer.py python
"""APK Code Analyzer — orchestrates androguard + JADX + apktool analysis.

This is the APK equivalent of BinaryNinjaDecompiler in
redb/extractors/decompiler/bninja/decompiler.py.
"""

import math
import os
import tempfile
from collections import Counter
from concurrent.futures import ThreadPoolExecutor, as_completed
from typing import Any, Dict, List, Optional, Set

from redb.extractors.decompiler.apk.apktool_wrapper import ApktoolDisassembler
from redb.extractors.decompiler.apk.jadx_wrapper import JADXDecompiler
from redb.extractors.decompiler.apk.library_filter import LibraryFilter
from redb.extractors.decompiler.apk.method_extractor import (
    compute_minhash,
    compute_prime_product_smali,
    compute_sha256,
    compute_ssdeep,
    compute_tlsh,
    count_call_instructions,
    dalvik_to_java_class,
    dalvik_to_java_prototype,
    detect_obfuscation_indicators,
)
from redb.extractors.decompiler.apk.smali_normalization import normalize_method_body
from redb.extractors.decompiler.apk.smali_cfg import compute_cfg_metrics
from redb.extractors.decompiler.apk.smali_parser import SmaliParser


class APKCodeAnalyzer:
    """Orchestrates APK code analysis combining three tools.

    Combines androguard (call graphs, xrefs, method enumeration),
    JADX (Java decompilation), and apktool (smali disassembly).
    """

    def __init__(
        self,
        filepath: str,
        timeout: int = 600,
        log=None,
        decompile_modules: Set[str] = None,
    ):
        self.filepath = filepath
        self.timeout = timeout
        self.log = log
        self.decompile_modules = decompile_modules or {"all"}
        self.min_instructions = int(
            os.getenv("APK_MIN_METHOD_INSTRUCTIONS", "5")
        )
        self.library_filter = LibraryFilter()
        self.jadx = JADXDecompiler(log=log)
        self.apktool = ApktoolDisassembler(log=log)

        self._temp_dirs = []

    def extract(self) -> Dict[str, Any]:
        """Run full APK code analysis.

        Returns dict with keys:
            decompiled_content, decompiled_refs,
            smali_content, smali_refs,
            similarity_metrics, strings, analysis_errors
        """
        results = {
            "decompiled_content": [],
            "decompiled_refs": [],
            "smali_content": [],
            "smali_refs": [],
            "similarity_metrics": [],
            "cfg": [],
            "strings": [],
            "analysis_errors": [],
        }

        # Create temp directories
        jadx_dir = tempfile.mkdtemp(prefix="redb_jadx_")
        apktool_dir = tempfile.mkdtemp(prefix="redb_apktool_")
        self._temp_dirs.extend([jadx_dir, apktool_dir])

        # Step 1-3: Run JADX, apktool, and androguard in parallel
        jadx_success = False
        apktool_success = False
        androguard_result = None

        with ThreadPoolExecutor(max_workers=3) as executor:
            futures = {}
            futures[executor.submit(self.jadx.decompile, self.filepath, jadx_dir)] = "jadx"
            futures[executor.submit(self.apktool.disassemble, self.filepath, apktool_dir)] = "apktool"
            futures[executor.submit(self._run_androguard)] = "androguard"

            for future in as_completed(futures):
                tool = futures[future]
                try:
                    result = future.result()
                    if tool == "jadx":
                        jadx_success = result
                    elif tool == "apktool":
                        apktool_success = result
                    elif tool == "androguard":
                        androguard_result = result
                except Exception as e:
                    if self.log:
                        self.log.error(f"{tool} failed: {e}")
                    results["analysis_errors"].append({
                        "class_name": None,
                        "method_name": None,
                        "error_location": tool,
                        "error_message": str(e),
                        "error_type": type(e).__name__,
                    })

        if androguard_result is None:
            if self.log:
                self.log.error("Androguard analysis failed — cannot proceed")
            return results

        apk_obj, dexs, analysis = androguard_result

        # Step 4b: Extract strings from DEX files
        try:
            results["strings"] = self._extract_strings(dexs)
        except Exception as e:
            if self.log:
                self.log.error(f"String extraction failed: {e}")
            results["analysis_errors"].append({
                "class_name": None,
                "method_name": None,
                "error_location": "strings",
                "error_message": f"String extraction failed: {e}",
                "error_type": type(e).__name__,
            })

        # Step 5: Parse smali output
        smali_methods = {}
        if apktool_success:
            try:
                smali_dirs = self.apktool.get_smali_directories(apktool_dir)
                for sdir in smali_dirs:
                    smali_methods.update(SmaliParser.parse_smali_directory(sdir))
            except Exception as e:
                if self.log:
                    self.log.error(f"Smali parsing failed: {e}")
                results["analysis_errors"].append({
                    "class_name": None,
                    "method_name": None,
                    "error_location": "apktool",
                    "error_message": f"Smali parsing failed: {e}",
                    "error_type": type(e).__name__,
                })

        # Step 6: Parse Java output
        java_methods = {}
        if jadx_success:
            try:
                java_methods = self.jadx.parse_java_methods(jadx_dir)
            except Exception as e:
                if self.log:
                    self.log.error(f"Java parsing failed: {e}")
                results["analysis_errors"].append({
                    "class_name": None,
                    "method_name": None,
                    "error_location": "jadx",
                    "error_message": f"Java parsing failed: {e}",
                    "error_type": type(e).__name__,
                })

        if not apktool_success and self.log:
            self.log.info(
                "apktool failed — falling back to androguard disassembly"
            )

        # Step 7-8: Process each method from androguard
        seen_decompiled_hashes = set()
        seen_smali_hashes = set()

        try:
            for method in analysis.get_methods():
                try:
                    self._process_method(
                        method,
                        smali_methods,
                        java_methods,
                        results,
                        seen_decompiled_hashes,
                        seen_smali_hashes,
                    )
                except Exception as e:
                    method_name = "unknown"
                    class_name = "unknown"
                    try:
                        if not method.is_external():
                            enc = method.get_method()
                            class_name = enc.get_class_name()
                            method_name = enc.get_name()
                    except Exception:
                        pass
                    results["analysis_errors"].append({
                        "class_name": class_name,
                        "method_name": method_name,
                        "error_location": "analysis",
                        "error_message": str(e),
                        "error_type": type(e).__name__,
                    })
        except Exception as e:
            if self.log:
                self.log.error(f"Method enumeration failed: {e}")
            results["analysis_errors"].append({
                "class_name": None,
                "method_name": None,
                "error_location": "androguard",
                "error_message": f"Method enumeration failed: {e}",
                "error_type": type(e).__name__,
            })

        if self.log:
            stats = self.library_filter.get_filter_stats()
            self.log.info(
                f"APK analysis complete: {stats['user']} user methods, "
                f"{stats['library']} library methods filtered, "
                f"{len(results['decompiled_content'])} decompiled, "
                f"{len(results['smali_content'])} smali, "
                f"{len(results['strings'])} strings"
            )

        return results

    def _run_androguard(self):
        """Run androguard analysis on the APK."""
        from androguard.misc import AnalyzeAPK
        return AnalyzeAPK(self.filepath)

    def _process_method(
        self,
        method,
        smali_methods: Dict,
        java_methods: Dict,
        results: Dict,
        seen_decompiled: set,
        seen_smali: set,
    ):
        """Process a single method from androguard analysis."""
        # Skip external methods (no code body)
        if method.is_external():
            return

        encoded = method.get_method()
        class_name = encoded.get_class_name()
        method_name = encoded.get_name()
        descriptor = encoded.get_descriptor()

        # Build method key for cross-tool matching
        method_key = SmaliParser.make_method_key(class_name, method_name, descriptor)

        # Check if library
        is_lib = self.library_filter.is_library(class_name)
        method_type = "LIBRARY" if is_lib else "USER"

        # Skip library methods for content tables (but they're still in xrefs)
        if is_lib:
            return

        # Get xrefs
        # In androguard 4.x, xref tuples are (ClassAnalysis, MethodAnalysis, offset).
        # The MethodAnalysis wrapper doesn't expose get_class_name()/get_name()
        # directly — we need to unwrap via .get_method() first.
        callers = []
        callees = []
        try:
            for ref_class, ref_method, offset in method.get_xref_from():
                try:
                    enc = ref_method.get_method()
                    caller_key = f"{enc.get_class_name()}->{enc.get_name()}"
                except AttributeError:
                    # Fallback for older androguard where ref_method is EncodedMethod
                    caller_key = f"{ref_method.get_class_name()}->{ref_method.get_name()}"
                callers.append(caller_key)
        except Exception:
            pass

        try:
            for ref_class, ref_method, offset in method.get_xref_to():
                try:
                    enc = ref_method.get_method()
                    callee_key = f"{enc.get_class_name()}->{enc.get_name()}"
                except AttributeError:
                    callee_key = f"{ref_method.get_class_name()}->{ref_method.get_name()}"
                callees.append(callee_key)
        except Exception:
            pass

        # Look up smali body
        smali_method = smali_methods.get(method_key)
        smali_body = None
        smali_normalized = None
        smali_hash = None
        instruction_count = 0
        register_count = 0

        if smali_method:
            smali_body = smali_method.body
            instruction_count = smali_method.instruction_count
            register_count = smali_method.register_count
        else:
            # Fallback: use androguard's own disassembler
            smali_body, instruction_count, register_count = (
                self._disassemble_with_androguard(encoded)
            )

        # Apply minimum instruction filter
        if instruction_count < self.min_instructions:
            return

        if smali_body:
            smali_normalized = SmaliParser.normalize_smali_body(smali_body)
            if smali_normalized:
                smali_hash = compute_sha256(smali_normalized)

        if not smali_hash:
            return

        # Compute obfuscation indicators from smali
        obfuscation = detect_obfuscation_indicators(
            method_name, class_name, smali_body, instruction_count
        )

        # Compute CFG metrics early — needed for both content tables and cfg table
        cfg_metrics = None
        if smali_body:
            try:
                cfg_metrics = compute_cfg_metrics(smali_body)
            except Exception:
                pass

        # Smali content (deduplicated)
        if smali_hash and smali_hash not in seen_smali:
            seen_smali.add(smali_hash)
            results["smali_content"].append({
                "smali_method_hash": smali_hash,
                "smali_method": smali_body,
                "smali_method_type": method_type,
                "smali_instructions_count": instruction_count,
                "smali_register_count": register_count,
                "smali_has_string_encryption": obfuscation.get("has_string_encryption", False),
                "smali_has_reflection_calls": obfuscation.get("has_reflection_calls", False),
                "smali_excessive_goto_count": obfuscation.get("excessive_goto_count", False),
                "smali_flattened_score": cfg_metrics.flattened_score if cfg_metrics else 0.0,
                "smali_mba_score": cfg_metrics.mba_score if cfg_metrics else 0.0,
            })

        # Smali reference (per-binary)
        ssdeep_val = compute_ssdeep(smali_normalized) if smali_normalized else None
        tlsh_val = compute_tlsh(smali_normalized) if smali_normalized else None

        # Semantically normalized ssdeep/TLSH (analogous to Binja's ssdeep_llil/tlsh_llil)
        ssdeep_normalized_val = None
        tlsh_normalized_val = None
        if smali_normalized:
            normalized_lines = normalize_method_body(smali_normalized, level="opcode_api")
            if normalized_lines:
                normalized_text = "\n".join(normalized_lines)
                ssdeep_normalized_val = compute_ssdeep(normalized_text)
                tlsh_normalized_val = compute_tlsh(normalized_text)

        # Look up Java source
        java_class = dalvik_to_java_class(class_name)
        java_key_candidates = [
            f"{java_class}.{method_name}",
        ]
        java_source = None
        decompiled_hash = None

        for jk in java_key_candidates:
            for key, source in java_methods.items():
                if key.startswith(jk):
                    java_source = source
                    break
            if java_source:
                break

        if java_source:
            # Normalize and hash decompiled content
            normalized_java = _normalize_java(java_source)
            decompiled_hash = compute_sha256(normalized_java)

            # Decompiled content (deduplicated)
            if decompiled_hash not in seen_decompiled:
                seen_decompiled.add(decompiled_hash)
                results["decompiled_content"].append({
                    "decompiled_method_hash": decompiled_hash,
                    "decompiled_method": java_source,
                    "decompiled_method_type": method_type,
                    "decompiled_has_string_encryption": obfuscation.get("has_string_encryption", False),
                    "decompiled_has_reflection_calls": obfuscation.get("has_reflection_calls", False),
                    "decompiled_excessive_goto_count": obfuscation.get("excessive_goto_count", False),
                })

            # Decompiled reference
            method_prototype = dalvik_to_java_prototype(
                method_name, descriptor, class_name
            )
            results["decompiled_refs"].append({
                "decompiled_method_hash": decompiled_hash,
                "smali_method_hash": smali_hash,
                "decompiled_class_name": dalvik_to_java_class(class_name),
                "decompiled_method_name": method_name,
                "decompiled_method_signature": descriptor,
                "decompiled_method_prototype": method_prototype,
                "functions_caller": callers,
                "functions_call": callees,
            })

        # Smali reference
        if smali_hash:
            results["smali_refs"].append({
                "smali_method_hash": smali_hash,
                "decompiled_method_hash": decompiled_hash,
                "smali_class_name": dalvik_to_java_class(class_name),
                "smali_method_name": method_name,
                "smali_method_signature": descriptor,
                "ssdeep_smali": ssdeep_val,
                "tlsh_smali": tlsh_val,
            })

        # Similarity metrics (content-based fuzzy matching only)
        if smali_hash and smali_normalized:
            minhash_sig = compute_minhash(smali_normalized)
            sim_entry = {
                "smali_method_hash": smali_hash,
                "cyclomatic_complexity": cfg_metrics.cyclomatic_complexity if cfg_metrics else None,
                "ssdeep_smali": ssdeep_val,
                "tlsh_smali": tlsh_val,
                "ssdeep_smali_normalized": ssdeep_normalized_val,
                "tlsh_smali_normalized": tlsh_normalized_val,
                "minhash": minhash_sig or [],
            }
            results["similarity_metrics"].append(sim_entry)

        # CFG entry (structural/topological features)
        if smali_hash and cfg_metrics and smali_body:
            prime_product = compute_prime_product_smali(smali_body)
            call_count = count_call_instructions(smali_body)
            cfg_entry = {
                "smali_method_hash": smali_hash,
                "cfg_topology_hash": cfg_metrics.cfg_topology_hash,
                "block_count": cfg_metrics.block_count,
                "edge_count": cfg_metrics.edge_count,
                "cfg_instructions_count": instruction_count,
                "call_count": call_count,
                "cyclomatic_complexity": cfg_metrics.cyclomatic_complexity,
                "loop_count": cfg_metrics.loop_count,
                "max_depth": cfg_metrics.max_depth,
                "max_fan_out": cfg_metrics.max_fan_out,
                "md_index_topdown": cfg_metrics.md_index_topdown,
                "md_index_bottomup": cfg_metrics.md_index_bottomup,
                "prime_product_smali": prime_product,
                "cfg_feature_tlsh": cfg_metrics.cfg_feature_tlsh,
                "wl_minhash": cfg_metrics.wl_minhash,
                "bb_features": cfg_metrics.block_features,
                "cfg_adjacency": cfg_metrics.cfg_adjacency,
            }
            results["cfg"].append(cfg_entry)

    @staticmethod
    def _string_entropy(s: str) -> float:
        """Compute Shannon entropy of a string."""
        if not s:
            return 0.0
        freq = Counter(s)
        length = len(s)
        return -sum(
            (count / length) * math.log2(count / length)
            for count in freq.values()
        )

    def _extract_strings(self, dexs) -> List[Dict[str, Any]]:
        """Extract deduplicated strings from all DEX objects.

        Uses androguard's get_strings() on each DEX, deduplicates by value,
        and computes entropy — matching the Binja StringAnalysis output format
        so IOCExtractorFromResults can consume them identically.

        Returns list of dicts with keys:
            string, string_encoding, string_offset, string_length, string_entropy
        """
        seen = set()
        strings = []
        offset_counter = 0

        for dex in dexs:
            try:
                dex_strings = dex.get_strings()
            except Exception:
                continue

            if not dex_strings:
                continue

            for s in dex_strings:
                if not s or s in seen:
                    continue
                # DEX MUTF-8 strings may contain unpaired surrogates (e.g. \ud800)
                # that are invalid UTF-8 and will fail ClickHouse insert
                s = s.encode('utf-8', errors='replace').decode('utf-8')
                if not s or s in seen:
                    continue
                seen.add(s)

                strings.append({
                    "string": s,
                    "string_encoding": "UTF8",
                    "string_offset": offset_counter,
                    "string_length": len(s),
                    "string_entropy": self._string_entropy(s),
                })
                offset_counter += 1

        return strings

    @staticmethod
    def _disassemble_with_androguard(encoded):
        """Fallback disassembly using androguard when apktool fails.

        Returns (smali_body, instruction_count, register_count).
        """
        code = encoded.get_code()
        if not code:
            return None, 0, 0

        register_count = code.get_registers_size()
        lines = []
        instruction_count = 0

        try:
            bytecode = code.get_bc()
            if not bytecode:
                return None, 0, register_count

            for instruction in bytecode.get_instructions():
                op_name = instruction.get_name()
                output = instruction.get_output()
                if output:
                    output = _normalize_androguard_operands(op_name, output)
                    lines.append(f"    {op_name} {output}")
                else:
                    lines.append(f"    {op_name}")
                instruction_count += 1
        except Exception:
            return None, 0, register_count

        if not lines:
            return None, 0, register_count

        smali_body = "\n".join(lines)
        return smali_body, instruction_count, register_count

    def cleanup(self):
        """Remove temporary directories."""
        import shutil
        for d in self._temp_dirs:
            try:
                if os.path.isdir(d):
                    shutil.rmtree(d)
            except Exception:
                pass
        self._temp_dirs.clear()


def _normalize_androguard_operands(op_name: str, output: str) -> str:
    """Normalize androguard instruction output to match apktool smali format.

    Androguard's get_output() differs from apktool in two key ways:
    1. invoke-* operands lack {braces} around registers:
       androguard: 'v0, v1, Lcom/Foo;->bar()V'
       apktool:    '{v0, v1}, Lcom/Foo;->bar()V'
    2. Field instructions use a space instead of colon between name and type:
       androguard: 'v0, v1, LA;->field Ljava/lang/String;'
       apktool:    'v0, v1, LA;->field:Ljava/lang/String;'
    """
    # invoke-* instructions: wrap register args in {braces}
    if op_name.startswith("invoke-"):
        # Find the class/method reference (starts with L or [)
        # Split on ', ' and find where the reference begins
        parts = output.split(", ")
        reg_parts = []
        ref_idx = None
        for i, part in enumerate(parts):
            stripped = part.strip()
            if stripped.startswith("L") or stripped.startswith("["):
                ref_idx = i
                break
            reg_parts.append(part)

        if ref_idx is not None and reg_parts:
            regs = ", ".join(reg_parts)
            ref = ", ".join(parts[ref_idx:])
            return "{" + regs + "}, " + ref
        elif reg_parts:
            # No reference found — just wrap all as registers
            return "{" + ", ".join(reg_parts) + "}"

    # Field instructions: fix 'field Ltype;' → 'field:Ltype;'
    if op_name.startswith(("iget", "iput", "sget", "sput")):
        # Pattern: '... ClassName;->fieldName Ltype;' or '... ClassName;->fieldName [Ltype;'
        # The space between fieldName and the type descriptor should be a colon
        arrow_idx = output.find("->")
        if arrow_idx != -1:
            after_arrow = output[arrow_idx + 2:]
            # Find the space before the type descriptor
            space_idx = after_arrow.find(" ")
            if space_idx != -1:
                remaining = after_arrow[space_idx + 1:]
                # Check that what follows is a type descriptor
                if remaining.startswith(("L", "[", "Z", "B", "S", "C",
                                         "I", "J", "F", "D")):
                    after_arrow = after_arrow[:space_idx] + ":" + remaining
                    output = output[:arrow_idx + 2] + after_arrow

    return output


def _normalize_java(source: str) -> str:
    """Normalize Java source for consistent hashing.

    Strip leading/trailing whitespace, normalize indentation.
    """
    lines = []
    for line in source.split("\n"):
        stripped = line.strip()
        if stripped:
            lines.append(stripped)
    return "\n".join(lines)