Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
消解器揭示了概念消除中非线性防护的成本
机构 * Michigan State University(密歇根州立大学)
AI总结 本文提出Obliviator方法,通过迭代优化消除非线性依赖,揭示消除过程中属性保护与效用保持之间的动态关系,其消解-效用权衡曲线优于基线方法。
Comments Accepted to NeurIPS 2025 [Poster]. Code available at: https://github.com/ramin-akbari/Obliviator
Journal ref The Thirty-Ninth Annual Conference on Neural Information Processing Systems 2025