The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication. This trend has heightened the need for reliable detection methods to distinguish between human-authored and machine-generated content. Existing approaches both zero-shot methods and supervised classifiers largely conceptualize this task as a binary classification problem, often leading to poor generalization across domains and models. In this paper, we argue that such a binary formulation fundamentally mischaracterizes the detection task by assuming a coherent representation of human-written texts. In reality, human texts do not constitute a unified distribution, and their diversity cannot be effectively captured through limited sampling. This causes previous classifiers to memorize observed OOD characteristics rather than learn the essence of `non-ID' behavior, limiting generalization to unseen human-authored inputs. Based on this observation, we propose reframing the detection task as an out-of-distribution (OOD) detection problem, treating human-written texts as distributional outliers while machine-generated texts are in-distribution (ID) samples. To this end, we develop a detection framework using one-class learning method including DeepSVDD and HRN, and score-based learning techniques such as energy-based method, enabling robust and generalizable performance. Extensive experiments across multiple datasets validate the effectiveness of our OOD-based approach. Specifically, the OOD-based method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset. Moreover, we test our detection framework on multilingual, attacked, and unseen-model and -domain text settings, demonstrating the robustness and generalizability of our framework. Code, pretrained weights, and demo will be released.

We thank the reviewers for their insightful feedback. In the following, we address their concerns and questions. ": There is a big misunderstanding. The table above shows that the proposed model performs best. ": Deep SVDD uses only one center and one layer, while we have multiple centers ( 's, the key challenge is on what contribution Indeed, these have been discussed at lines 115-116 and 126-128.

Semi-supervised anomaly detection, which aims to improve the performance of the anomaly detector by using a small amount of anomaly data in addition to unlabeled data, has attracted attention. Existing semi-supervised approaches assume that unlabeled data are mostly normal. They train the anomaly detector to minimize the anomaly scores for the unlabeled data, and to maximize those for the anomaly data. However, in practice, the unlabeled data are often contaminated with anomalies. This weakens the effect of maximizing the anomaly scores for anomalies, and prevents us from improving the detection performance. To solve this problem, we propose the positive-unlabeled autoencoder, which is based on positive-unlabeled learning and the anomaly detector such as the autoencoder. With our approach, we can approximate the anomaly scores for normal data using the unlabeled and anomaly data. Therefore, without the labeled normal data, we can train the anomaly detector to minimize the anomaly scores for normal data, and to maximize those for the anomaly data. In addition, our approach is applicable to various anomaly detectors such as the DeepSVDD. Experiments on various datasets show that our approach achieves better detection performance than existing approaches.

When dealing with text data containing subjective labels like speaker emotions, inaccuracies or discrepancies among labelers are not uncommon. Such discrepancies can significantly affect the performance of machine learning algorithms. This study investigates the potential of identifying and addressing outliers in text data with subjective labels, aiming to enhance classification outcomes. We utilized the Deep SVDD algorithm, a one-class classification method, to detect outliers in nine text-based emotion and sentiment analysis datasets. By employing both a small-sized language model (DistilBERT base model with 66 million parameters) and non-deep learning machine learning algorithms (decision tree, KNN, Logistic Regression, and LDA) as the classifier, our findings suggest that the removal of outliers can lead to enhanced results in most cases. Additionally, as outliers in such datasets are not necessarily unlearnable, we experienced utilizing a large language model -- DeBERTa v3 large with 131 million parameters, which can capture very complex patterns in data. We continued to observe performance enhancements across multiple datasets.

Outlier detection (OD) literature exhibits numerous algorithms as it applies to diverse domains. However, given a new detection task, it is unclear how to choose an algorithm to use, nor how to set its hyperparameter(s) (HPs) in unsupervised settings. HP tuning is an ever-growing problem with the arrival of many new detectors based on deep learning, which usually come with a long list of HPs. Surprisingly, the issue of model selection in the outlier mining literature has been "the elephant in the room"; a significant factor in unlocking the utmost potential of deep methods, yet little said or done to systematically tackle the issue. In the first part of this paper, we conduct the first large-scale analysis on the HP sensitivity of deep OD methods, and through more than 35,000 trained models, quantitatively demonstrate that model selection is inevitable. Next, we design a HP-robust and scalable deep hyper-ensemble model called ROBOD that assembles models with varying HP configurations, bypassing the choice paralysis. Importantly, we introduce novel strategies to speed up ensemble training, such as parameter sharing, batch/simultaneous training, and data subsampling, that allow us to train fewer models with fewer parameters. Extensive experiments on both image and tabular datasets show that ROBOD achieves and retains robust, state-of-the-art detection performance as compared to its modern counterparts, while taking only $2$-$10$\% of the time by the naive hyper-ensemble with independent training.

We study anomaly detection for the case when the normal class consists of more than one object category. This is an obvious generalization of the standard one-class anomaly detection problem. However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together. We further develop a new anomaly detector called DeepMAD that learns compact distinguishing features by exploiting the multiple normal objects categories. This algorithm achieves higher AUC values for different datasets compared to two top performing one-class algorithms that either are trained on each normal object category or jointly trained on all normal object categories combined. In addition to theoretical results we present empirical results using the CIFAR-10, fMNIST, CIFAR-100, and a new dataset we developed called RECYCLE.

Classical approaches for one-class problems such as one-class SVM (Scholkopf et al., 1999) and isolation forest (Liu et al., 2008) require careful feature engineering when applied to structured domains like images. To alleviate this concern, state-of-the-art methods like DeepSVDD (Ruff et al., 2018) consider the natural alternative of minimizing a classical one-class loss applied to the learned final layer representations. However, such an approach suffers from the fundamental drawback that a representation that simply collapses all the inputs minimizes the one class loss; heuristics to mitigate collapsed representations provide limited benefits. In this work, we propose Deep Robust One Class Classification (DROCC) method that is robust to such a collapse by training the network to distinguish the training points from their perturbations, generated adversarially. DROCC is motivated by the assumption that the interesting class lies on a locally linear low dimensional manifold. Empirical evaluation demonstrates DROCC's effectiveness on two different one-class problem settings and on a range of real-world datasets across different domains - images(CIFAR and ImageNet), audio and timeseries, offering up to 20% increase in accuracy over the state-of-the-art in anomaly detection.