Adaptive Causal Alignment for High-Confidence Adversarial Training 事件

Adaptive Causal Alignment for High-Confidence Adversarial Training arXiv:2606.03925v1 Announce Type: new Abstract: Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual-natured signal, serving as either a necessary supportive prior