Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks? explores A framework to assess and defend LLM-enhanced Graph Neural Networks against sophisticated poisoning attacks, with released code for broader research.. Commercial viability score: 7/10 in GNN Security.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisPoisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor AttacksViability: 5.0
- Builds On ThisPIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation SystemsViability: 4.0
- Builds On ThisFraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud AttacksViability: 3.0
- Builds On ThisKEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented GenerationViability: 4.0
- Builds On ThisBeyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models