Nan Xu

38 papers A* 7A 3B 1C 3Journal 16Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
Pattern Recognit.
Jingxuan Wei, Nan Xu, Guiyong Chang, Yin Luo, Bihui Yu, Ruifeng Guo
2025 J jnl
CoRR
Minzheng Wang, Yongbin Li, Haobo Wang, Xinghua Zhang, Nan Xu, Bingli Wu, Fei Huang, Haiyang Yu, Wenji Mao
2025 conf
ACL (Findings)
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
2025 conf
NAACL (Findings)
Yuan Tian, Minzheng Wang, Nan Xu, Wenji Mao
2025 J jnl
CoRR
Zhaoyu Ma, Yuan Shan, Jiahao Zhao, Nan Xu, Lei Wang
2025 J jnl
CoRR
Jiahao Zhao, Shuaixing Zhang, Nan Xu, Lei Wang
2024 conf
NAACL-HLT
Yuan Tian, Nan Xu, Wenji Mao
2024 conf
ACL (1)
Yuan Tian, Ruike Zhang, Nan Xu, Wenji Mao
2024 J jnl
CoRR
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
2024 A* conf
EMNLP
Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
2024 J jnl
CoRR
Minzheng Wang, Longze Chen, Cheng Fu, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
2024 A* conf
CVPR
Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Tsung-Yi Ho, Nan Xu, Qiang Xu
2024 conf
LREC/COLING
Minzheng Wang, Nan Xu, Jiahao Zhao, Yin Luo, Wenji Mao
2024 J jnl
CoRR
Jingxuan Wei, Nan Xu, Guiyong Chang, Yin Luo, Bihui Yu, Ruifeng Guo
2023 C conf
ISI
Ruike Zhang, Nan Xu, Wenji Mao, Daniel Zeng
2023 J jnl
IEEE Trans. Multim.
Nan Xu, Junyan Wang, Yuan Tian, Ruike Zhang, Wenji Mao
2023 C conf
ISI
Hanyi Zou, Nan Xu, Qingchao Kong, Wenji Mao
2023 conf
ACL (1)
Yuan Tian, Nan Xu, Ruike Zhang, Wenji Mao
2023 J jnl
CoRR
Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Nan Xu, Qiang Xu
2023 A* conf
EMNLP
Yuan Tian, Nan Xu, Wenji Mao, Daniel Zeng
2023 conf
ACL (Findings)
Ruike Zhang, Nan Xu, Hanxuan Yang, Yuan Tian, Wenji Mao
2023 J jnl
CoRR
Yin Luo, Qingchao Kong, Nan Xu, Jia Cao, Bao Hao, Baoyu Qu, Bo Chen, Chao Zhu, Chenyang Zhao, Donglei Zhang, Fan Feng, Feifei Zhao, Hailong Sun, Hanxuan Yang, Haojun Pan, Hongyu Liu, Jianbin Guo, Jiangtao Du, Jingyi Wang, Junfeng Li, Lei Sun, Liduo Liu, Lifeng Dong, Lili Liu, Lin Wang, Liwen Zhang, Minzheng Wang, Pin Wang, Ping Yu, Qingxiao Li, Rui Yan, Rui Zou, Ruiqun Li, Taiwen Huang, Xiaodong Wang, Xiaofei Wu, Xin Peng, Xina Zhang, Xing Fang, Xinglin Xiao, Yanni Hao, Yao Dong, Yigang Wang, Ying Liu, Yongyu Jiang, Yungan Wang, Yuqi Wang, Zhangsheng Wang, Zhaoxin Yu, Zhen Luo, Wenji Mao, Lei Wang, Daniel Dajun Zeng
2023 J jnl
CoRR
Xinglin Xiao, Yijie Wang, Nan Xu, Yuqi Wang, Hanxuan Yang, Minzheng Wang, Yin Luo, Lei Wang, Wenji Mao, Daniel Zeng
2022 J jnl
IEEE Intell. Syst.
Zhixiong Zeng, Nan Xu, Wenji Mao, Daniel Zeng
2021 C conf
ISI
Yuan Tian, Nan Xu, Wenji Mao, Yin Luo
2021 J jnl
CoRR
Nan Xu, Junyan Wang, Yuan Tian, Ruike Zhang, Wenji Mao
2021 J jnl
IEEE Intell. Syst.
Nan Xu, Wenji Mao, Penghui Wei, Daniel Zeng
2021 A* conf
SIGIR
Zhixiong Zeng, Shuai Wang, Nan Xu, Wenji Mao
2020 A conf
CIKM
Zhixiong Zeng, Nan Xu, Wenji Mao
2020 A* conf
ACL
Nan Xu, Zhixiong Zeng, Wenji Mao
2019 conf
EMNLP/IJCNLP (1)
Penghui Wei, Nan Xu, Wenji Mao
2019 J jnl
CoRR
Penghui Wei, Nan Xu, Wenji Mao
2019 A* conf
AAAI
Nan Xu, Wenji Mao, Guandan Chen
2019 J jnl
Neurocomputing
Guandan Chen, Qingchao Kong, Nan Xu, Wenji Mao
2018 A* conf
SIGIR
Nan Xu, Wenji Mao, Guandan Chen
2018 A conf
CIKM
Guandan Chen, Nan Xu, Wenji Mao
2018 B conf
IJCNN
Nan Xu, Guandan Chen, Wenji Mao
2017 A conf
CIKM
Nan Xu, Wenji Mao
redb/extractors/js_extractors/js_deobfuscator.py
← Index redb/extractors/js_extractors/js_deobfuscator.py python
"""Subprocess-driven JavaScript deobfuscator with jsbeautifier fallback.

Owns the heavy lifting that was previously embedded inside
`JSDeobfuscationExtractor` (`_run_deobfuscator` + `_try_jsbeautifier`). Exposed
as a single module-level entry point `deobfuscate(source, log)` so it can be
called from `JSContext.deobfuscated` (cached per sample) without dragging
extractor state through the call.

Configuration (env vars):
    JS_DEOBFUSCATOR_PATH    Path or name of the external tool (default: webcrack).
    JS_DEOBFUSCATE_TIMEOUT  Seconds before the external tool is killed
                            (process-group SIGTERM, then SIGKILL). Default: 60.

If the external tool produces non-empty output and exits 0, that wins. Otherwise
the source is run through jsbeautifier (which only normalises formatting, but
already exposes strings hidden by minification). If neither path produces
output, returns (None, None).

`FileNotFoundError` for the external tool is treated as routine — the analysis
server is either provisioned with the tool or it isn't — and demoted to a
debug-level log.
"""

import os
import signal
import subprocess
import tempfile
from typing import Optional, Tuple

DEFAULT_DEOBFUSCATOR = "webcrack"
DEFAULT_TIMEOUT_SECS = 60


def _run_external(
    source: str, deobfuscator_path: str, timeout: int, log
) -> Tuple[Optional[str], int]:
    """Run the configured external deobfuscator over `source` and capture stdout.

    Returns (text, returncode). `text` is `None` and `returncode` is `-1` when
    the binary is missing, the run timed out, or any other unexpected failure
    occurred. Missing-binary is logged at debug; timeouts and unexpected errors
    surface at warning/error.
    """
    try:
        with tempfile.NamedTemporaryFile(
            suffix=".js", mode="w", delete=False, encoding="utf-8"
        ) as tmp:
            tmp.write(source)
            tmp_path = tmp.name

        try:
            process = subprocess.Popen(
                [deobfuscator_path, tmp_path],
                stdout=subprocess.PIPE,
                stderr=subprocess.PIPE,
                preexec_fn=os.setsid,
            )

            try:
                stdout, _ = process.communicate(timeout=timeout)
                return stdout.decode("utf-8", errors="replace"), process.returncode
            except subprocess.TimeoutExpired:
                # Kill the entire process group so spawned helpers (e.g. node
                # subprocesses webcrack itself launches) get cleaned up too.
                try:
                    os.killpg(os.getpgid(process.pid), signal.SIGTERM)
                    process.wait(timeout=5)
                except Exception:
                    try:
                        os.killpg(os.getpgid(process.pid), signal.SIGKILL)
                    except Exception:
                        pass
                log.warning(f"Deobfuscation timed out after {timeout}s")
                return None, -1
        finally:
            try:
                os.unlink(tmp_path)
            except Exception:
                pass
    except FileNotFoundError:
        log.debug(f"Deobfuscator binary not found at {deobfuscator_path}")
        return None, -1
    except Exception as e:
        log.error(f"Error running deobfuscator: {e}")
        return None, -1


def _try_jsbeautifier(source: str, log) -> Tuple[Optional[str], Optional[str]]:
    """Fallback path: format the source with jsbeautifier. Returns
    `(text, "jsbeautifier")` or `(None, None)` if jsbeautifier isn't installed
    or the call raised."""
    try:
        import jsbeautifier
        opts = jsbeautifier.default_options()
        opts.indent_size = 2
        return jsbeautifier.beautify(source, opts), "jsbeautifier"
    except ImportError:
        log.debug("jsbeautifier not available")
        return None, None
    except Exception as e:
        log.warning(f"jsbeautifier failed: {e}")
        return None, None


def deobfuscate(source: str, log) -> Tuple[Optional[str], Optional[str]]:
    """Run the configured external deobfuscator, falling back to jsbeautifier.

    Returns `(text, normalizer_used)` on success, or `(None, None)` when neither
    path produced non-empty output. `normalizer_used` is the basename of the
    external tool (e.g. `"webcrack"`) or the literal `"jsbeautifier"`.
    """
    if not source:
        return None, None

    deobfuscator_path = os.getenv("JS_DEOBFUSCATOR_PATH", DEFAULT_DEOBFUSCATOR)
    timeout = int(os.getenv("JS_DEOBFUSCATE_TIMEOUT", str(DEFAULT_TIMEOUT_SECS)))

    text, returncode = _run_external(source, deobfuscator_path, timeout, log)
    if text and returncode == 0 and text.strip():
        return text, os.path.basename(deobfuscator_path)

    return _try_jsbeautifier(source, log)