Timber!毒化决策树
Timber! Poisoning Decision Trees
AI总结:
提出首个针对决策树的白盒毒化攻击Timber,基于贪心策略与子树重训练高效估计损害并支持早停,实验证明其优于基线且现有防御难以有效阻止。
摘要:
我们提出了Timber,这是首个针对决策树的白盒毒化攻击。Timber基于一种贪心攻击策略,该策略利用子树重训练来高效估计毒化给定训练实例所造成的损害。该攻击依赖于一个树标注过程,它能够对训练实例进行排序,使其按照子树重训练计算成本递增的顺序进行处理。这种排序产生了一种Timber变体,该变体支持早停准则,旨在使毒化攻击在更大数据集上更加高效和可行。我们还讨论了Timber向传统随机森林模型的扩展,这很有价值,因为决策树通常被组合成集成模型以提升预测能力。我们在公开数据集上的实验评估表明,我们的攻击在有效性、效率或两者兼有方面优于现有基线。此外,我们展示了两类代表性防御措施可以减轻攻击影响,但未能有效阻止它们。
英文摘要:
We present Timber, the first white-box poisoning attack targeting decision trees. Timber is based on a greedy attack strategy that leverages sub-tree retraining to efficiently estimate the damage caused by poisoning a given training instance. The attack relies on a tree annotation procedure, which enables the sorting of training instances so that they are processed in increasing order of the computational cost of sub-tree retraining. This sorting yields a variant of Timber that supports an early stopping criterion, designed to make poisoning attacks more efficient and feasible on larger datasets. We also discuss an extension of Timber to traditional random forest models, which is valuable since decision trees are typically combined into ensembles to improve their predictive power. Our experimental evaluation on public datasets demonstrates that our attacks outperform existing baselines in terms of effectiveness, efficiency, or both. Moreover, we show that two representative defenses can mitigate the effect of our attacks, but fail to effectively thwart them.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。