GoAT-X introduces a novel framework that structures cross-chain smart contract auditing as a Graph of Auditing Thoughts, significantly improving the detection of complex, semantic vulnerabilities in m…

AttackPathGNN proposes a novel graph neural network approach to detect smart contract vulnerabilities by modeling explicit attack paths and function interactions, achieving high detection rates on sta…

ContractShield is a robust multimodal framework that uses a novel three-level fusion mechanism to accurately detect multiple types of vulnerabilities in obfuscated smart contracts, significantly outpe…

VulGD is a dynamic, open-access graph database that aggregates cybersecurity data from multiple sources and uses LLM embeddings to improve vulnerability representation and risk assessment.

The paper introduces Phoenix, a training-free multi-agent framework that detects code vulnerabilities by synthesizing project-specific behavioral contracts, significantly outperforming existing method…

The paper introduces Bastet, a novel, high-quality, expert-labeled dataset designed to overcome limitations in existing resources for detecting complex smart contract vulnerabilities in DeFi.

GenDetect introduces a novel framework to rapidly generalize detection rules from single observed DeFi exploits, significantly improving resilience against subsequent, similar 'Imitative Attack Cascad…

The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due…

The paper introduces an efficient, lightweight LLM framework for smart contract auditing that decouples the audit process into multiple components, achieving high accuracy while significantly reducing…

The paper introduces an LLM-based framework that uses vulnerability-specific prompting and a large-scale dataset to achieve high-precision, scalable detection of multiple smart contract vulnerabilitie…

This paper outlines a comprehensive research framework for smart contract security, moving beyond simple vulnerability detection to encompass advanced areas like semantic reasoning, automated repair,…

The paper introduces Oracle Poisoning, an attack that corrupts knowledge graphs used by AI agents, demonstrating that all tested models blindly trust poisoned data at high sophistication levels.

LibScan is an automated framework that detects eight categories of smart contract library misuse by combining LLM-based semantic reasoning with rule-based analysis, achieving 85.15% accuracy on real-w…

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

The paper proposes a graph-learning approach to predict multi-vulnerability attack chains within software supply chains, achieving high accuracy on both component classification and cascade prediction…

The paper introduces AgentFlow, a novel framework that uses a typed graph DSL and feedback-driven optimization to automatically synthesize and improve multi-agent harnesses for discovering security vu…

The paper introduces HackerSignal, a massive, multi-source benchmark dataset that uniquely links hacker community discourse to the entire CVE vulnerability lifecycle, enabling advanced temporal cyber…

HunterAgent is a neuro-symbolic framework that reconstructs causal attack chains from fragmented, anti-forensics-corrupted logs, achieving high accuracy while drastically reducing hallucination.

The paper proposes a graph-based framework for detecting attacks in LLM agent tool-call traffic, finding that content-level embeddings are crucial for high accuracy and that tree ensembles on these em…

Knowdit is a knowledge-driven, agentic framework that significantly improves smart contract vulnerability detection by modeling shared DeFi semantics and leveraging historical audit knowledge.