Successful malware campaigns rely on Command-and-Control (C2) infrastructure, enabling attackers to extract sensitive data and give instructions to bots. As a resilient mechanism to obtain C2 endpoints, attackers can employ Domain Generation Algorithms (DGAs), which automatically generate C2 domains instead of relying on static ones. Thus, researchers have proposed network-level detection approaches that reveal DGA usage by differentiating between non-DGA and generated domains. Recent approaches train machine learning (ML) models to recognize DGA domains using pattern recognition at the domain’s character level.

Recent breakthroughs in machine learning (ML) have unleashed several approaches to fingerprinting web traffic based on traffic analysis. In particular, researchers report impressive classification performances by modeling HTTPS traces using packet metadata. Recent works focus mainly on the packet burst metadata (packet lengths, counts, and directions). The fact that burst metadata characterizes web traces is not surprising per se. Then again, most works stop at providing evaluation results and do not question the reasons for the success in qualitative analyses or ablation studies.

Synthetic data is becoming an increasingly promising technology, and successful applications can improve privacy, fairness, and data democratization. While there are many methods for generating synthetic tabular data, the task remains non-trivial and unexplored for specific scenarios. One such scenario is survival data. Here, the key difficulty is censoring: for some instances, we are not aware of the time of event, or if one even occurred. Imbalances in censoring and time horizons cause generative models to experience three new failure modes specific to survival analysis: (1) generating too few at-risk members; (2) generating too many at-risk members; and (3) censoring too early. We formalize these failure modes and provide three new generative metrics to quantify them. Following this, we propose SurvivalGAN, a generative model that handles survival data firstly by addressing the imbalance in the censoring and event horizons, and secondly by using a dedicated mechanism for approximating time-to-event/censoring. We evaluate this method via extensive experiments on medical datasets. SurvivalGAN outperforms multiple baselines at generating survival data, and in particular addresses the failure modes as measured by the new metrics, in addition to improving downstream performance of survival models trained on the synthetic data.

Consider the problem of imputing missing values in a dataset. One the one hand, conventional approaches using iterative imputation benefit from the simplicity and customizability of learning conditional distributions directly, but suffer from the practical requirement for appropriate model specification of each and every variable. On the other hand, recent methods using deep generative modeling benefit from the capacity and efficiency of learning with neural network function approximators, but are often difficult to optimize and rely on stronger data assumptions. In this work, we study an approach that marries the advantages of both: We propose *HyperImpute*, a generalized iterative imputation framework for adaptively and automatically configuring column-wise models and their hyperparameters. Practically, we provide a concrete implementation with out-of-the-box learners, optimizers, simulators, and extensible interfaces. Empirically, we investigate this framework via comprehensive experiments and sensitivities on a variety of public datasets, and demonstrate its ability to generate accurate imputations relative to a strong suite of benchmarks. Contrary to recent work, we believe our findings constitute a strong defense of the iterative imputation paradigm.