Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
–Neural Information Processing Systems
Adversarial training [10, 16, 18], which injects adversarially perturbed dataintotraining data,isapromising approach. Many other heuristics have been developed to make neural networks insensitive against small perturbations on inputs.
Neural Information Processing Systems
Feb-12-2026, 17:57:35 GMT
- Country:
- Asia
- Japan > Honshū
- Kantō > Tokyo Metropolis Prefecture > Tokyo (0.06)
- Middle East > Israel
- Haifa District > Haifa (0.04)
- Japan > Honshū
- North America > Canada
- Asia
- Technology: