# ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment

arXiv: https://arxiv.org/abs/2603.28128 · HTML: https://mlsanity.com/paper/2603.28128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 84 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 30 of 32)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2107.11598/) (2021)
- [Assessing Adversarial Robustness of Large Language Models: An Empirical Study](https://mlsanity.com/paper/2405.02764/) (2024)
- [How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection](https://mlsanity.com/paper/2005.11613/) (2020)
- [Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation](https://mlsanity.com/paper/2404.15687/) (2024)
- [DAppSCAN: Building Large-Scale Datasets for Smart Contract Weaknesses in DApp Projects](https://mlsanity.com/paper/2305.08456/) (2023)
- [Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/2208.06651/) (2022)
- [Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems](https://mlsanity.com/paper/2401.14886/) (2024)
- [SCALM: Detecting Bad Practices in Smart Contracts Through LLMs](https://mlsanity.com/paper/2502.04347/) (2025)
- [HGAttack: Transferable Heterogeneous Graph Adversarial Attack](https://mlsanity.com/paper/2401.09945/) (2024)
- [EtherSolve: Computing an Accurate Control-Flow Graph from Ethereum Bytecode](https://mlsanity.com/paper/2103.09113/) (2021)
- [SC-Bench: A Large-Scale Dataset for Smart Contract Auditing](https://mlsanity.com/paper/2410.06176/) (2024)
- [Consolidation of Ground Truth Sets for Weakness Detection in Smart Contracts](https://mlsanity.com/paper/2304.11624/) (2023)
- [Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration](https://mlsanity.com/paper/2602.05708/) (2026)
- [Smart Contract Vulnerabilities, Tools, and Benchmarks: an Updated Systematic Literature Review](https://mlsanity.com/paper/2412.01719/) (2024)
- [MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation](https://mlsanity.com/paper/2502.16955/) (2025)
- [An empirical analysis of vulnerability detection tools for solidity smart contracts](https://mlsanity.com/paper/2505.15756/) (2025)

## Abstract (arXiv)

Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations. Homogeneous graph models fail to capture the interplay between control flow and data dependencies, while heterogeneous graph approaches often lack deep semantic understanding, leaving them susceptible to adversarial attacks. Moreover, most black-box models fail to provide explainable evidence, hindering trust in professional audits. To address these challenges, we propose ORACAL (Observable RAG-enhanced Analysis with CausAL reasoning), a heterogeneous multimodal graph learning framework that integrates Control Flow Graph (CFG), Data Flow Graph (DFG), and Call Graph (CG). ORACAL selectively enriches critical subgraphs with expert-level security context from Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs), and employs a causal attention mechanism to disentangle true vulnerability indicators from spurious correlations. For transparency, the framework adopts PGExplainer to generate subgraph-level explanations identifying vulnerability triggering paths. Experiments on large-scale datasets demonstrate that ORACAL achieves state-of-the-art performance, outperforming MANDO-HGT, MTVHunter, GNN-SC, and SCVHunter by up to 39.6 percentage points, with a peak Macro F1 of 91.28% on the primary benchmark. ORACAL maintains strong generalization on out-of-distribution datasets with 91.8% on CGT Weakness and 77.1% on DAppScan. In explainability evaluation, PGExplainer achieves 32.51% Mean Intersection over Union (MIoU) against manually annotated vulnerability triggering paths. Under adversarial attacks, ORACAL limits performance degradation to approximately 2.35% F1 decrease with an Attack Success Rate (ASR) of only 3%, surpassing SCVHunter and MANDO-HGT which exhibit ASRs ranging from 10.91% to 18.73%.