SafeDD: A Mask-and-Retrain Defense Framework for Backdoor Mitigation in Dataset Distillation
Xianjia Meng, JiaHao Xie
Northwest University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Dataset distillation has emerged as a promising technique to compress large-scale datasets into small synthetic sets, significantly reducing training overhead. However, this paradigm introduces a critical security vulnerability: malicious providers can embed hidden backdoors into the distilled data, causing downstream models to misclassify triggered inputs. Defending against such attacks in the distillation setting presents a unique challenge due to the extreme scarcity of synthetic samples (e.g., 10 images per class). Conventional defenses, which rely on filtering or discarding suspicious samples, fail in this regime as removing high-density samples leads to a catastrophic collapse in model utility. To address this dilemma, we propose SafeDD, a novel defense framework based on a Mask-andRetrain strategy. Our approach formulates an optimization objective to decouple and extract dominant features from synthetic images. We optimize a mask to eliminate these influential features and subsequently retrain the model to evaluate the impact. The core insight leverages the shortcut learning phenomenon: we posit that the dominant features in poisoned samples converge to the backdoor trigger, whereas in benign samples, they correspond to critical semantic content. Consequently, masking these features effectively neutralizes the backdoor in poisoned classes while retaining sufficient semantic information for classification. Extensive experiments demonstrate that SafeDD successfully reduces the attack success rate to near 0% and maintains robust recognition accuracy on the targeted malicious classes.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAdversarial Robustness in Machine Learning
Digital Media Forensic Detection · Security and Verification in Computing