SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.08108 · 2022

Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2212.08108.json · badge: /api/ran/2212.08108.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ISU-PAAL/DeepDFA canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_examples_to_features Ran
ran; our contract draft was wrong, not the code
ISU-PAAL/DeepDFA/LineVul/linevul/linevul_main.py
code served (permissive licence) · get_code("d351b03eb53efa20")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned InputFeatures. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

class MockTokenizer:
    def __init__(self):
        self.cls_token = "[CLS]"
        self.sep_token = "[SEP]"
        self.pad_token_id = 0
    
    def tokenize(self, text):
        return text.split()[:100]
    
    def convert_tokens_to_ids(self, tokens):
        return [hash(token) % 1000 for token in tokens]
    
    def encode(self, text):
        class Encoded:
            def __init__(self):
                self.ids = [0] + [hash(word) % 1000 for word in text.split()[:508]] + [2]
        return Encoded()

class MockArgs:
    def __init__(self):
        self.use_word_level_tokenizer = False
        self.block_size = 512

func_code = "def hello_world():\n    return 42"
label = 1
tokenizer = MockTokenizer()
args = MockArgs()
i = 0

ARGS = {
    "func": func_code,
    "label": label,
    "tokenizer": tokenizer,
    "args": args,
    "i": i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type InputFeatures — a InputFeatures output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InputFeatures output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
evaluate Ran
ran on a synthesized input
ISU-PAAL/DeepDFA/LineVul/linevul/linevul_main.py
code served (permissive licence) · get_code("44312da6e0a58c0a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import numpy as np
from torch.utils.data import Dataset

torch.manual_seed(0)
np.random.seed(0)

# Create a minimal model that matches the function's usage
class MinimalModel(nn.Module):
    def forward(self, input_ids, labels, graphs):
        batch_size = input_ids.shape[0]
        # Return (loss, logits)
        loss = torch.tensor(0.5)
        # Binary classification logits: [batch_size, 2]
        logits = torch.randn(batch_size, 2)
        return loss, logits

# Create a minimal tokenizer
class MinimalTokenizer:
    pass

# Create a minimal args object
class Args:
    def __init__(self):
        self.eval_batch_size = 2
        self.n_gpu = 1
        self.device = torch.device('cpu')

# Create a minimal dataset
class MinimalDataset(Dataset):
    def __init__(self, size=4):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        # Return (input_ids, labels, index)
        input_ids = torch.randint(0, 100, (3,))
        labels = torch.tensor(np.random.randint(0, 2), dtype=torch.long)
        index = torch.tensor(idx, dtype=torch.long)
        return input_ids, labels, index

# Create a minimal flowgnn_dataset
class MinimalFlowGNNDataset:
    def get_indices(self, index):
        # Return (graphs, keep_idx)
        graphs = None
        keep_idx = torch.arange(len(index))
        return graphs, keep_idx

# Construct the arguments
args = Args()
model = MinimalModel()
tokenizer = MinimalTokenizer()
eval_dataset = MinimalDataset(size=4)
flowgnn_dataset = MinimalFlowGNNDataset()

ARGS = {
    'args': args,
    'model': model,
    'tokenizer': tokenizer,
    'eval_dataset': eval_dataset,
    'flowgnn_dataset': flowgnn_dataset,
    'eval_when_training': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing approaches use token-based transformer models, which are not the most efficient to capture code semantics required for vulnerability detection. Classical program analysis techniques such as dataflow analysis can detect many types of bugs based on their root causes. In this paper, we propose to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection. Specifically, we designed DeepDFA, a dataflow analysis-inspired graph learning framework and an embedding technique that enables graph learning to simulate dataflow computation. We show that DeepDFA is both performant and efficient. DeepDFA outperformed all non-transformer baselines. It was trained in 9 minutes, 75x faster than the highest-performing baseline model. When using only 50+ vulnerable and several hundreds of total examples as training data, the model retained the same performance as 100% of the dataset. DeepDFA also generalized to real-world vulnerabilities in DbgBench; it detected 8.7 out of 17 vulnerabilities on average across folds and was able to distinguish between patched and buggy versions, while the highest-performing baseline models did not detect any vulnerabilities. By combining DeepDFA with a large language model, we surpassed the state-of-the-art vulnerability detection performance on the Big-Vul dataset with 96.46 F1 score, 97.82 precision, and 95.14 recall. Our replication package is located at https://doi.org/10.6084/m9.figshare.21225413 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2212.08108")
get_code_for_paper("2212.08108")
have("2212.08108")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2212.08108.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2212.08108.svg)](https://syntology.ai/paper/2212.08108)

Connect an agent — have() is free.