GHOST: GAN-Harnessed Optimization for Strategic Backdoor Persistence With Future Update Anticipation in Non-IID Federated Learning

Summary

GHOST is a two-phase backdoor attack on federated learning that pairs a dual-discriminator GAN with multi-round anticipation. The GAN generates synthetic samples aligned with the global data distribution, which the attacker uses to simulate future FL rounds and optimize a poisoning update for long-term survival. Experiments on several vision datasets show more durable backdoor persistence than prior methods, including under norm-bounding and FoolsGold, with competitive clean accuracy.

Related items

• InfoVGPD-FL: Group-level poisoning detection without trusted datasets for secure aggregationSimilar attack · Elsevier Security Journals
• InfoFedPSA: Adaptive Backdoor Attacks on Federated Large Language Models via Poisoning Sensitive Prompt LayersSimilar attack · IEEE Xplore (Security & AI Journals)
• InfoTAFL: Trust-Aware Federated Learning for Anomalous Client Detection, Isolation, and RecoverySimilar attack · IEEE Xplore (Security & AI Journals)
• InfoFederated backdoor attack with aggregated triggers optimized by maximum mean discrepancySimilar attack · OpenAlex (peer-reviewed AI security)
• LowLLM Trojans that Increase Response Lengths and CostSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)