2026
Parameter-Efficient Dual-Loss Adaptation with Logit Divergence: A Unified Approach for Adversarial Example Detection and Robust Inference
IJCAI 2026
We present D3Adapter, a threat-aware framework that unifies adversarial example detection (AED) and robust inference. D3Adapter attaches a small library of lightweight adapters to a frozen ResNet backbone; the adapters are trained under two loss functions (cross-entropy and optimized reverse cross-e