Mobile devices increasingly require the parallel execution of several computing tasks offloaded at the wireless edge. Existing communication systems only support parallel transmissions at the bit level, which fundamentally limits the number of tasks that can be concurrently processed. To address this bottleneck, this paper introduces the new concept of Semantic Multiplexing. Our approach shifts stream multiplexing from bits to tasks by merging multiple task-related compressed representations into a single semantic representation. As such, Semantic Multiplexing can multiplex more tasks than the number of physical channels without adding antennas or widening bandwidth by extending the effective degrees of freedom at the semantic layer, without contradicting Shannon capacity rules. We have prototyped Semantic Multiplexing on an experimental testbed with Jetson Orin Nano and millimeter-wave software-defined radios and tested its performance on image classification and sentiment analysis while comparing to several existing baselines in semantic communications. Our experiments demonstrate that Semantic Multiplexing allows jointly processing multiple tasks at the semantic level while maintaining sufficient task accuracy. For example, image classification accuracy drops by less than 4% when increasing from 2 to 8 the number of tasks multiplexed over a 4$\times$4 channel. Semantic Multiplexing reduces latency, energy consumption, and communication load respectively by up to 8$\times$, 25$\times$, and 54$\times$ compared to the baselines while keeping comparable performance. We pledge to publicly share the complete software codebase and the collected datasets for reproducibility.

Deep ensembles (DE) have emerged as a powerful approach for quantifying predictive uncertainty and distinguishing its aleatoric and epistemic components, thereby enhancing model robustness and reliability. However, their high computational and memory costs during inference pose significant challenges for wide practical deployment. To overcome this issue, we propose credal ensemble distillation (CED), a novel framework that compresses a DE into a single model, CREDIT, for classification tasks. Instead of a single softmax probability distribution, CREDIT predicts class-wise probability intervals that define a credal set, a convex set of probability distributions, for uncertainty quantification. Empirical results on out-of-distribution detection benchmarks demonstrate that CED achieves superior or comparable uncertainty estimation compared to several existing baselines, while substantially reducing inference overhead compared to DE.

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated texts. However, recent findings suggest that these techniques often negatively affect the quality of the generated texts, and adversarial attacks can strip the watermarking signals, causing the texts to possibly evade detection. These findings have created resistance in the wide adoption of watermarking by LLM creators. Finally, to encourage adoption, we evaluate the robustness of several watermarking techniques to adversarial attacks by comparing paraphrasing and back translation (i.e., English $\to$ another language $\to$ English) attacks; and their ability to preserve quality and writing style of the unwatermarked texts by using linguistic metrics to capture quality and writing style of texts. Our results suggest that these watermarking techniques preserve semantics, deviate from the writing style of the unwatermarked texts, and are susceptible to adversarial attacks, especially for the back translation attack.

The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable performance. Previous approaches typically establish scoring metrics based on specific criteria to identify representative samples. However, these methods predominantly rely on sample scores obtained from the model's performance during the training (i.e., fitting) phase. As scoring models achieve near-optimal performance on training data, such fitting-centric approaches induce a dense distribution of sample scores within a narrow numerical range. This concentration reduces the distinction between samples and hinders effective selection. To address this challenge, we conduct dataset pruning from the perspective of generalization, i.e., scoring samples based on models not exposed to them during training. We propose a plug-and-play framework, UNSEEN, which can be integrated into existing dataset pruning methods. Additionally, conventional score-based methods are single-step and rely on models trained solely on the complete dataset, providing limited perspective on the importance of samples. To address this limitation, we scale UNSEEN to multi-step scenarios and propose an incremental selection technique through scoring models trained on varying coresets, and optimize the quality of the coreset dynamically. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art (SOTA) methods on CIFAR-10, CIFAR-100, and ImageNet-1K. Notably, on ImageNet-1K, UNSEEN achieves lossless performance while reducing training data by 30\%.

The widespread reliance on open-source software dramatically increases the risk of vulnerability exploitation, underscoring the need for effective and scalable vulnerability detection (VD). Existing VD techniques, whether traditional machine learning-based or LLM-based approaches like prompt engineering, supervised fine-tuning, or off-policy preference optimization, remain fundamentally limited in their ability to perform context-aware analysis: They depend on fixed inputs or static preference datasets, cannot adaptively explore repository-level dependencies, and are constrained by function-level benchmarks that overlook critical vulnerability context. This paper introduces Vulnerability-Adaptive Policy Optimization (VULPO), an on-policy LLM reinforcement learning framework for context-aware VD. To support training and evaluation, we first construct ContextVul, a new dataset that augments high-quality function-level samples with lightweight method to extract repository-level context information. We then design multi-dimensional reward structuring that jointly captures prediction correctness, vulnerability localization accuracy, and the semantic relevance of vulnerability analysis, thereby guiding the model toward comprehensive contextual reasoning. To address the asymmetric difficulty of different vulnerability cases and mitigate reward hacking, VULPO incorporates label-level and sample-level difficulty-adaptive reward scaling, encouraging the model to explore challenging cases while maintaining balanced reward distribution. Extensive experiments demonstrate the superiority of our VULPO framework in context-aware VD: Our VULPO-4B substantially outperforms existing VD baselines based on prompt engineering and off-policy optimization, improving F1 by 85% over Qwen3-4B and achieving performance comparable to a 150x larger-scale model, DeepSeek-R1-0528.

AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI systems may be deployed in safety-critical settings, including to help ensure the safety of future systems. Unfortunately, frontier and future systems may not be sufficiently trustworthy, and there is evidence that these systems may even be misaligned with their developers or users. Therefore, we investigate the capabilities of AI agents to act against the interests of their users when conducting ML engineering, by sabotaging ML models, sandbagging their performance, and subverting oversight mechanisms. First, we extend MLE-Bench, a benchmark for realistic ML tasks, with code-sabotage tasks such as implanting backdoors and purposefully causing generalisation failures. Frontier agents make meaningful progress on our sabotage tasks. In addition, we study agent capabilities to sandbag on MLE-Bench. Agents can calibrate their performance to specified target levels below their actual capability. To mitigate sabotage, we use LM monitors to detect suspicious agent behaviour, and we measure model capability to sabotage and sandbag without being detected by these monitors. Overall, monitors are capable at detecting code-sabotage attempts but our results suggest that detecting sandbagging is more difficult. Additionally, aggregating multiple monitor predictions works well, but monitoring may not be sufficiently reliable to mitigate sabotage in high-stakes domains. Our benchmark is implemented in the UK AISI's Inspect framework and we make our code publicly available at https://github.com/TeunvdWeij/ctrl-alt-deceit

Automatic sleep staging plays a vital role in assessing sleep quality and diagnosing sleep disorders. Most existing methods rely heavily on long and continuous EEG recordings, which poses significant challenges for data acquisition in resource-constrained systems, such as wearable or home-based monitoring systems. In this paper, we propose the task of resource-efficient sleep staging, which aims to reduce the amount of signal collected per sleep epoch while maintaining reliable classification performance. To solve this task, we adopt the masking and prompt learning strategy and propose a novel framework called Mask-A ware Sleep Staging (MASS). Specifically, we design a multi-level masking strategy to promote effective feature modeling under partial and irregular observations. To mitigate the loss of contextual information introduced by masking, we further propose a hierarchical prompt learning mechanism that aggregates unmasked data into a global prompt, serving as a semantic anchor for guiding both patch-level and epoch-level feature modeling. MASS is evaluated on four datasets, demonstrating state-of-the-art performance, especially when the amount of data is very limited. This result highlights its potential for efficient and scalable deployment in real-world low-resource sleep monitoring environments.

The rapid expansion of Internet of Things (IoT) devices has transformed industries and daily life by enabling widespread connectivity and data exchange. However, this increased interconnection has introduced serious security vulnerabilities, making IoT systems more exposed to sophisticated cyber attacks. This study presents a novel ensemble learning architecture designed to improve IoT attack detection. The proposed approach applies advanced machine learning techniques, specifically the Extra Trees Classifier, along with thorough preprocessing and hyperparameter optimization. It is evaluated on several benchmark datasets including CICIoT2023, IoTID20, BotNeTIoT L01, ToN IoT, N BaIoT, and BoT IoT. The results show excellent performance, achieving high recall, accuracy, and precision with very low error rates. These outcomes demonstrate the model efficiency and superiority compared to existing approaches, providing an effective and scalable method for securing IoT environments. This research establishes a solid foundation for future progress in protecting connected devices from evolving cyber threats.

Anomaly detection is critical in domains such as cybersecurity and finance, especially when working with large-scale tabular data. Yet, unsupervised anomaly detection-where no labeled anomalies are available-remains challenging because traditional deep learning methods model a single global distribution, assuming all samples follow the same behavior. In contrast, real-world data often contain heterogeneous contexts (e.g., different users, accounts, or devices), where globally rare events may be normal within specific conditions. We introduce a contextual learning framework that explicitly models how normal behavior varies across contexts by learning conditional data distributions $P(\mathbf{Y} \mid \mathbf{C})$ rather than a global joint distribution $P(\mathbf{X})$. The framework encompasses (1) a probabilistic formulation for context-conditioned learning, (2) a principled bilevel optimization strategy for automatically selecting informative context features using early validation loss, and (3) theoretical grounding through variance decomposition and discriminative learning principles. We instantiate this framework using a novel conditional Wasserstein autoencoder as a simple yet effective model for tabular anomaly detection. Extensive experiments across eight benchmark datasets demonstrate that contextual learning consistently outperforms global approaches-even when the optimal context is not intuitively obvious-establishing a new foundation for anomaly detection in heterogeneous tabular data.

Machine learning based predictions are increasingly used in sensitive decision-making applications that directly affect our lives. This has led to extensive research into ensuring the fairness of classifiers. Beyond just fair classification, emerging legislation now mandates that when a classifier delivers a negative decision, it must also offer actionable steps an individual can take to reverse that outcome. This concept is known as algorithmic recourse. Nevertheless, many researchers have expressed concerns about the fairness guarantees within the recourse process itself. In this work, we provide a holistic theoretical characterization of unfairness in algorithmic recourse, formally linking fairness guarantees in recourse and classification, and highlighting limitations of the standard equal cost paradigm. We then introduce a novel fairness framework based on social burden, along with a practical algorithm (MISOB), broadly applicable under real-world conditions. Empirical results on real-world datasets show that MISOB reduces the social burden across all groups without compromising overall classifier accuracy.