Lihe Zhang

Long-tailed adversarial training can be revolutionized by leveraging confusion geometry to boost the robustness of vulnerable classes and sharpen critical decision boundaries.

CoreUnlearn enables targeted erasure of harmful concepts in diffusion models without sacrificing performance, redefining ethical standards in AI-generated content.

Low-confidence training samples are secretly sabotaging your fast adversarial training, leading to catastrophic overfitting and a worse robustness-accuracy trade-off.

Catastrophic overfitting in fast adversarial training isn't just overfitting – it's a backdoor, and now we can use backdoor defenses to fix it.