Recent research has shown the vulnerability of Spiking Neural Networks (SNNs) under adversarial examples that are nearly indistinguishable from clean data in the context of frame-based and event-based information. The majority of these studies are constrained in generating adversarial examples using Backpropagation Through Time (BPTT), a gradient-based method which lacks biological plausibility. In contrast, local learning methods, which relax many of BPTT's constraints, remain under-explored in the context of adversarial attacks. To address this problem, we examine adversarial robustness in SNNs through the framework of four types of training algorithms. We provide an in-depth analysis of the ineffectiveness of gradient-based adversarial attacks to generate adversarial instances in this scenario. To overcome these limitations, we introduce a hybrid adversarial attack paradigm that leverages the transferability of adversarial instances. The proposed hybrid approach demonstrates superior performance, outperforming existing adversarial attack methods. Furthermore, the generalizability of the method is assessed under multi-step adversarial attacks, adversarial attacks in black-box FGSM scenarios, and within the non-spiking domain.

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model, violating intellectual property. While novel attacks in the field are continually being published, their design and evaluations are not standardised, making it challenging to compare prior works and assess progress in the field. This paper is the first to address this gap by providing recommendations for designing and evaluating model stealing attacks. To this end, we study the largest group of attacks that rely on training a substitute model -- those attacking image classification models. We propose the first comprehensive threat model and develop a framework for attack comparison. Further, we analyse attack setups from related works to understand which tasks and models have been studied the most. Based on our findings, we present best practices for attack development before, during, and beyond experiments and derive an extensive list of open research questions regarding the evaluation of model stealing attacks. Our findings and recommendations also transfer to other problem domains, hence establishing the first generic evaluation methodology for model stealing attacks.

Data minimization is a legal principle requiring personal data processing to be limited to what is necessary for a specified purpose. Operationalizing this principle for recommender systems, which rely on extensive personal data, remains a significant challenge. This paper conducts a feasibility study on minimizing implicit feedback inference data for such systems. We propose a novel problem formulation, analyze various minimization techniques, and investigate key factors influencing their effectiveness. We demonstrate that substantial inference data reduction is technically feasible without significant performance loss. However, its practicality is critically determined by two factors: the technical setting (e.g., performance targets, choice of model) and user characteristics (e.g., history size, preference complexity). Thus, while we establish its technical feasibility, we conclude that data minimization remains practically challenging and its dependence on the technical and user context makes a universal standard for data `necessity' difficult to implement.

Large Language Models (LLMs) have great potential to accelerate and support scholarly peer review and are increasingly used as fully automatic review generators (ARGs). However, potential biases and systematic errors may pose significant risks to scientific integrity; understanding the specific capabilities and limitations of state-of-the-art ARGs is essential. We focus on a core reviewing skill that underpins high-quality peer review: detecting faulty research logic. This involves evaluating the internal consistency between a paper's results, interpretations, and claims. We present a fully automated counterfactual evaluation framework that isolates and tests this skill under controlled conditions. Testing a range of ARG approaches, we find that, contrary to expectation, flaws in research logic have no significant effect on their output reviews. Based on our findings, we derive three actionable recommendations for future work and release our counterfactual dataset and evaluation framework publicly.

Fairness in recommender systems (RSs) is commonly categorised into group fairness and individual fairness. However, there is no established scientific understanding of the relationship between the two fairness types, as prior work on both types has used different evaluation measures or evaluation objectives for each fairness type, thereby not allowing for a proper comparison of the two. As a result, it is currently not known how increasing one type of fairness may affect the other. To fill this gap, we study the relationship of group and individual fairness through a comprehensive comparison of evaluation measures that can be used for both fairness types. Our experiments with 8 runs across 3 datasets show that recommendations that are highly fair for groups can be very unfair for individuals. Our finding is novel and useful for RS practitioners aiming to improve the fairness of their systems. Our code is available at: https://github.com/theresiavr/stairway-to-fairness.

Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucination detection methods often perform poorly on sentence-level generation or rely heavily on domain-specific knowledge. While self-consistency approaches help address these limitations, they incur high computational costs due to repeated generation. In this paper, we conduct the first study on identifying redundancy in self-consistency methods, manifested as shared prefix tokens across generations, and observe that non-exact-answer tokens contribute minimally to the semantic content. Based on these insights, we propose a novel Decoding Memory Pipeline (DMP) that accelerates generation through selective inference and annealed decoding. Being orthogonal to the model, dataset, decoding strategy, and self-consistency baseline, our DMP consistently improves the efficiency of multi-response generation and holds promise for extension to alignment and reasoning tasks. Extensive experiments show that our method achieves up to a 3x speedup without sacrificing AUROC performance.

Algorithmic hiring has become increasingly necessary in some sectors as it promises to deal with hundreds or even thousands of applicants. At the heart of these systems are algorithms designed to retrieve and rank candidate profiles, which are usually represented by Curricula Vitae (CVs). Research has shown, however, that such technologies can inadvertently introduce bias, leading to discrimination based on factors such as candidates' age, gender, or national origin. Developing methods to measure, mitigate, and explain bias in algorithmic hiring, as well as to evaluate and compare fairness techniques before deployment, requires sets of CVs that reflect the characteristics of people from diverse backgrounds. However, datasets of these characteristics that can be used to conduct this research do not exist. To address this limitation, this paper introduces an approach for building a synthetic dataset of CVs with features modeled on real materials collected through a data donation campaign. Additionally, the resulting dataset of 1,730 CVs is presented, which we envision as a potential benchmarking standard for research on algorithmic hiring discrimination.

The Deep Space Network (DSN) is NASA's largest network of antenna facilities that generate a large volume of multivariate time - series data. These facilities, situated at Canberra - Australia, Madrid - Spain, and Goldstone - California, contain DSN antennas and transmitters that undergo degradation over long periods of time, which may cause costly disruptions to the data flow and threaten the earth - connection of dozens of spacecraft that rely on the Deep Space Network for their lifeline. The purpose of this study was to experiment with different methods and tools that would be able to assist JPL engineers with directly pinpointing anomalies and DSN equipment degradation through collected data, and continue conducting maintenance and operations of the DSN for future space missions around our universe. As such, we have researched various machine learning techniques and architectures that can fully reconstruct data through predictive analysis, and determine anomalous data entries within real - time datasets through statistical computations and thresholds . On top of the fully trained and tested machine learning models, we have also integrated the use of a reinforcement learning subsystem that classifies identified anomalies based on severity level and a Large Language Model that labels an explanation for each anomalous data entry, all of which can be improved and fine - tuned over time through human feedback /input. Specifically, for the DSN transmitters, we have also implemented a full data pipeline system that connects the data extraction, parsing, and pro ces sing workflow all together as there was no coherent program or script for performing these tasks before. Using this data pipeline system, we were able to then also connect the models trained from DSN an tenna data, completing the data workflow for DSN anomaly detection . This was all wrapped around and further connected by an agentic AI system, where complex reasoning was utilized to determine the classifications and predictions of anomalous data .

In 2024, the "low-altitude economy" was written into China's Government Work Report for the first time [1], and flying robots have been rapidly popularized nationwide. From an environmental perspective, electrically powered air vehicles are attracting growing attention; key technologies include overall configuration design, integrated energy management, and high-efficiency, high power-to-weight electric propulsion [2]. For electric propulsion, mainstream systems use electric motors to drive propellers, but propeller noise is significant and hard to mitigate [3], which limits widespread use in cities--the main arena for the low-altitude economy--and is also unfavorable for silent reconnaissance. Hence, there is a pressing need for a new propulsion approach enabling quiet, fully electric flight. In the 1920s, Brown observed that an asymmetric capacitor under high voltage can generate thrust, known as the Biefeld-Brown effect. A leading explanation is ionic wind: a high electric field ionizes air, and the resulting ions accelerate and transfer momentum to neutral molecules, producing a net airflow (thrust) [4]. Xu et al. first mounted a plasma thruster on a fixed-wing UAV without other propulsion; the gliding distance with the thruster on was five times that with it off, but the maximum range was only 45m and no controller design was provided [5]. Zhang et al. realized altitude control for a micro ionic-wind-powered UA V using passive components, but the wingspan was at most 6 .3cm

Ukraine intends to strike deep into Russia following a large Russian drone attack that left 60,000 Ukrainians without electricity, President Volodymyr Zelenskyy has said. Speaking on Sunday after a meeting with his top general, Oleksandr Syrskii, the Ukrainian president confirmed the new planned strikes on X. Both sides have intensified their air strikes in recent weeks, with Moscow attacking Ukraine's energy and transport systems as well as launching deadly strikes in recent days on civilian areas in Kyiv and Zaporizhia, and Ukraine targeting Russian oil refineries and pipelines. Overnight, Russian drones hit four energy facilities in Ukraine's Odesa region, according to the private energy company DTEK. The strikes left 29,000 people without electricity, local authorities reported.