AINeutralarXiv – CS AI · 10h ago6/10
🧠
Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors
Researchers propose Cosine-Aware Adaptive Elastic Weight Consolidation (EWC) to improve text-to-image model backdoor attacks while maintaining model fidelity and generalization. The method addresses a fundamental trade-off between attack success and output quality by dynamically adjusting regularization weights based on semantic utility, achieving stronger performance on both in-domain and out-of-domain datasets compared to existing approaches.