Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce \textbf{Active Data Reconstruction Attack} (ADRA), a family of MIA that actively induces a model to reconstruct a given text through training. We hypothesize that training data are \textit{more reconstructible} than non-members, and the difference in their reconstructibility can be exploited for membership inference. Motivated by findings that reinforcement learning (RL) sharpens behaviors already encoded in weights, we leverage on-policy RL to actively elicit data reconstruction by finetuning a policy initialized from the target model. To effectively use RL for MIA, we design reconstruction metrics and contrastive rewards. The resulting algorithms, \textsc{ADRA} and its adaptive variant \textsc{ADRA+}, improve both reconstruction and detection given a pool of candidate data. Experiments show that our methods consistently outperform existing MIAs in detecting pre-training, post-training, and distillation data, with an average improvement of 10.7\% over the previous runner-up. In particular, \MethodPlus~improves over Min-K\%++ by 18.8\% on BookMIA for pre-training detection and by 7.6\% on AIME for post-training detection.
Predicting conditional probability distributions of redshifts of Active Galactic Nuclei using Hierarchical Correlation Reconstruction
Jagiellonian University(雅盖隆大学)
虽然一般关注于值的预测,但真实数据通常仅允许预测条件概率分布,其能力受条件熵$H(Y|X)$的限制。如果另外估计不确定性,我们可以将预测值视为拉普拉斯分布的高斯中心-理想化,其可以远离真实数据的复杂条件分布。本文应用分层相关重构(HCR)方法来廉价地预测相当复杂的条件概率分布(例如多峰):通过多个矩参数的独立MSE估计,这允许重构条件分布。为此目的使用线性回归,我们得到可解释的模型:用系数描述特征对条件矩的贡献。本文在原有方法的基础上进行了扩展,特别是采用典型相关分析(CCA)进行特征优化和l1“lasso”正则化,重点研究了基于Fourth Fermi-LAT Data Release 2(4LAC)数据集的活动星系核(AGN)红移预测的实际问题。