动态调整删除率，提升文本分类的抗扰动认证能力
AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
- 根据输入特性自适应调节删除率，突破固定删除率限制
- 在自然语言任务中，认证区域基数提升最高达30个数量级
- 适合需要高可信度防御的NLP安全应用
针对序列分类任务中基于编辑距离的扰动，现有方法因采用固定删除率导致性能不佳。本文提出AdaptDel方法，通过根据输入特征动态调整删除率，扩展随机平滑理论至可变删除率场景，实现对编辑距离的可靠认证。在自然语言处理任务中，该方法使认证区域的中位基数相比最先进方法提升高达30个数量级，显著增强模型鲁棒性。
原文摘要 · Abstract (English)
We consider the problem of certified robustness for sequence classification against edit distance perturbations. Naturally occurring inputs of varying lengths (e.g., sentences in natural language processing tasks) present a challenge to current methods that employ fixed-rate deletion mechanisms and lead to suboptimal performance. To this end, we introduce AdaptDel methods with adaptable deletion rates that dynamically adjust based on input properties. We extend the theoretical framework of randomized smoothing to variable-rate deletion, ensuring sound certification with respect to edit distance. We achieve strong empirical results in natural language tasks, observing up to 30 orders of magnitude improvement to median cardinality of the certified region, over state-of-the-art certifications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。