EvoPoC automates end-to-end exploit synthesis for DeFi vulnerabilities by organizing protocol knowledge into a hierarchical graph for LLM multi-hop reasoning, then validating reachability and profit via SMT solving and simulation, achieving 96.6% success on 88 real attacks.
Advanced smart contract vulnerability detection via llm-powered multi-agent systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
CAESAR decomposes LLM-based intrusion workflows into five roles with bounded coordination protocols, yielding higher success rates and lower variance than single-agent baselines on 25 CTF tasks.
citing papers explorer
-
EvoPoC: Automated Exploit Synthesis for DeFi Smart Contracts via Hierarchical Knowledge Graphs
EvoPoC automates end-to-end exploit synthesis for DeFi vulnerabilities by organizing protocol knowledge into a hierarchical graph for LLM multi-hop reasoning, then validating reachability and profit via SMT solving and simulation, achieving 96.6% success on 88 real attacks.
-
When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
CAESAR decomposes LLM-based intrusion workflows into five roles with bounded coordination protocols, yielding higher success rates and lower variance than single-agent baselines on 25 CTF tasks.