Explanations play a central role in shaping users’ trust and acceptance of autonomous vehicles (AVs). While existing AV explanation research has emphasized cognitive elements such as content, timing, and presentation fidelity, it offers limited guidance on how explanations might incorporate affective elements or adjust to varying driving contexts. To address this gap, we introduce a stance-strategy-tone framework for designing affective explanations, supported by scenario-specific guidelines and illustrative example utterances. Through interviews with seven domain experts and six co-design workshops involving 27 prospective AV users, we identified the components that influence how affective explanations are constructed and mapped them onto key driving scenarios. Our findings reveal design opportunities such as tailoring emotional framing to situational demands, combining empathy with informational clarity, and calibrating tone to balance warmth with directive precision. The study provides practical guidance for creating emotionally responsive explanation systems for AVs.

Shared living—where unrelated adults share domestic infrastructure—relies heavily on the interpretation of material traces: physical cues such as food arrangements, cleaning states, and object placements that residents produce and encounter asynchronously, largely without direct exchange. When the interpretive frame under which a cue is produced diverges from the frame under which it is decoded, coordination friction results. Through semi-structured interviews (N=13), we identify three interpretive frames—evidential, normative, and communicative—that residents apply to the same domestic cues, and document folk tuning: improvised strategies by which residents adjust three parameters—attribution, granularity, and temporality—to govern the distribution of ambiguity in shared space. A generative design workshop (N=20) then demonstrates how data physicalization can expand these parameters from constrained physical ranges into designable continua, yielding design orientations. We propose tunable ambiguity as a design concept that reframes ambiguity from a static artifact property to an inhabitant-controlled social process, and contribute actionable principles for interactive systems that support unspoken domestic coordination without collapsing into surveillance.

Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to efficiently design and deploy recent advanced models (e.g. transformers) on tiny devices due to their severe hardware resource constraints. In this work, we proposeTinyFormer, a framework specifically designed to develop and deploy resource-efficient transformer models on MCUs. TinyFormer consists ofSuperNAS,SparseNAS, andSparseEngine. Separately, SuperNAS aims to search for an appropriate supernet from a vast search space. SparseNAS evaluates the best sparse single-path transformer model from the identified supernet. Finally, SparseEngine efficiently deploys the searched sparse models onto MCUs. To the best of our knowledge, SparseEngine is the first deployment framework capable of performing inference of sparse transformer models on MCUs. Evaluation results on the CIFAR-10 dataset demonstrate that TinyFormer can design efficient transformers with an accuracy of 96.1% while adhering to hardware constraints of 1MB storage and 320KB memory. Additionally, TinyFormer achieves significant speedups in sparse inference, up to$12.2\times $comparing to the CMSIS-NN library. TinyFormer is believed to bring powerful transformers into TinyML scenarios and to greatly expand the scope of deep learning applications.

Arbitrary style transfer aims to apply artistic characteristics from a style reference to an image while preserving the image’s original content. Although many methods have achieved remarkable results in style transfer, they typically rely on largescale datasets for training, which increases both the cost and complexity of data collection. To address this issue, we propose a Low-rank Transformer Adaptation method for style transfer which leverages the efficiency of low-rank adaptation to reduce the model’s complexity without compromising performance. It not only accelerates the training process but also delivers high-quality image generation with a small-scale dataset. Additionally, we introduce an edge detection loss to enhance the preservation of content outlines further, ensuring that the fine details of the image are maintained during the style transfer process Experimental results demonstrate that our method achieves competitive performance even with significantly less data, and it exhibits superiority in both visual quality and evaluation metrics.

The rapid increase in the number of individuals with Autism Spectrum Disorder (ASD) has drawn extensive attention from both the general public and researchers. Artificial Intelligence (AI) has been applied in the assessment, early diagnosis, and intervention of ASD to enhance the efficiency of clinicians and reduce tension in medical resources. However, the adoption of AI systems in clinical practice is relatively limited due to the challenge of complexity and diversity of ASD. Thus, involving insights into clinicians' perceptions and barriers toward the role of AI is crucial for enhancing clinicians-AI cooperation for autism. Through conducting the semi-structured interview with 18 physicians across tertiary and secondary hospitals in various regions, this study indicates the positive attitude toward collaborating with AI among physicians. Additionally, some concerns are also reported, such as the complexity of ASD, uncertainty of AI capabilities, and understandability of AI. The findings of this study highlight the significance of human-centered AI in satisfying different stakeholders' needs and discuss the potential implications of AI capabilities for adopting AI in future autism research.

Arbitrary style transfer aims to render artistic features from a style reference onto an image while retaining its original content. Previous methods either focus on learning the holistic style from a specific artist or extracting instance features from a single artwork. However, they often fail to apply style elements uniformly across the entire image and lack adaptation to the style of different artworks. To solve these issues, our key insight is that the art genre has better generality and adaptability than the overall features of the artist. To this end, we propose a Dual-head Genre-instance Transformer (DGiT) framework to simultaneously capture the genre and instance features for arbitrary style transfer. To the best of our knowledge, this is the first work to integrate the genre features and instance features to generate a high-quality stylized image. Moreover, we design two contrastive losses to enhance the capability of the network to capture two style features. Our approach ensures the uniform distribution of the overall style across the stylized image while enhancing the details of textures and strokes in local regions. Qualitative and quantitative evaluations demonstrate that our approach exhibits superior visual quality and efficiency.

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated corpora have strong gender biases that can produce discriminative results in downstream tasks. Previous debiasing methods focus mainly on modeling bias and only implicitly consider semantic information while completely overlooking the complex underlying causal structure among bias and semantic components. To address these issues, we propose a novel methodology that leverages a causal inference framework to effectively remove gender bias. The proposed method allows us to construct and analyze the complex causal mechanisms facilitating gender information flow while retaining oracle semantic information within word embeddings. Our comprehensive experiments show that the proposed method achieves state-of-the-art results in gender-debiasing tasks. In addition, our methods yield better performance in word similarity evaluation and various extrinsic downstream NLP tasks.

The subtle and dynamic nature of insider threat makes it one of the most challenging problems in cyber security domain. Most of the existing studies model the problem from the perspective of user behavior, but the imbalance of data categories and the weak correlation between discrete behaviors are not considered simultaneously. To address these problems, we use reinforcement learning-based Generative Adversarial Network to synthesize high-quality minority class data, and use Word2Vec language model to learn the distance metric between different behaviors. In this paper, we propose a Resource Access Pattern Network (RAP-Net), which applies reinforcement learning-based Generative Adversarial Network, Word2Vec, Convolutional Neural Network, Recurrent Neural Network, and Attention Mechanism to insider threat detection. RAP-Net extracts user resource access pattern sequences from audit log files, and then performs data augmentation on the minority class sequences. After learning the distance metric of different tokens in sequences, feature vectors are sent to the classifier for anomaly detection. RAP-Net successfully addresses two major pain points in the current field, namely data imbalance and weak correlation of discrete behaviors. Intensive experimental results on the CMU-CERT r4.2 dataset demonstrate that RAP-Net outperforms state-of-the-art studies in the field.

Frequency hopping (FH) technology is one of the most effective technologies in the field of radio countermeasures, meanwhile, the recognition of FH signal has become a research hotspot. FH signal is a typical non-stationary signal whose frequency varies nonlinearly with time and the time-frequency analysis technique provides a very effective method for processing this kind of signal. With the renaissance of deep learning, methods based on time-frequency analysis and deep learning are widely studied. Although these methods have achieved good results, the recognition accuracy still needs to be improved. Through the observation of the datasets, we found that there are still difficult samples that are difficult to identify. Through further analysis, we propose a horizontal spatial attention (HSA) block, which can generate spatial weight vector according to the signal distribution, and then readjust the feature map. The HSA block is a plug-and-play module that can be integrated into common convolutional neural network (CNN) to further improve their performance and these networks with HSA block are collectively called HANets. The HSA block also has the advantages of high recognition accuracy (especially under low SNRs), easy to implant, and almost no influence on the number of parameters. We verified our method on two datasets and a series of comparative experiments show that the proposed method achieves good results on FH datasets.

Algorithmic fairness has received increased attention in socially sensitive domains. While rich literature on mean fairness has been established, research on quantile fairness remains sparse but vital. To fulfill great needs and advocate the significance of quantile fairness, we propose a novel framework to learn a real-valued quantile function under the fairness requirement of Demographic Parity with respect to sensitive attributes, such as race or gender, and thereby derive a reliable fair prediction interval. Using optimal transport and functional synchronization techniques, we establish theoretical guarantees of distribution-free coverage and exact fairness for the induced prediction interval constructed by fair quantiles. A hands-on pipeline is provided to incorporate flexible quantile regressions with an efficient fairness adjustment post-processing algorithm. We demonstrate the superior empirical performance of this approach on several benchmark datasets. Our results show the model’s ability to uncover the mechanism underlying the fairness-accuracy trade-off in a wide range of societal and medical applications.

Currently, more and more malicious insiders are making threats, and the detection of insider threats is becoming more challenging. The malicious insider often uses legitimate access privileges and mimic normal behaviors to evade detection, which is difficult to be detected via using traditional defensive solutions. In this paper, we propose DeepMIT, a malicious insider threat detection framework, which utilizes Recurrent Neural Network (RNN) to model user behaviors as time sequences and predict the probabilities of anomalies. This framework allows DeepMIT to continue learning, and the detections are made in real time, that is, the anomaly alerts are output as rapidly as data input. Also, our framework conducts further insight of the anomaly scores and provides the contributions to the scores and, thus, significantly helps the operators to understand anomaly scores and take further steps quickly(e.g. Block insider's activity). In addition, DeepMIT utilizes user-attributes (e.g. the personality of the user, the role of the user) as categorical features to identify the user's truly typical behavior, which help detect malicious insiders who mimic normal behaviors. Extensive experimental evaluations over a public insider threat dataset CERT (version 6.2) have demonstrated that DeepMIT has outperformed other existing malicious insider threat solutions.

With the widespread application of frequency hop-ping (FH) technology, a large number of FH signal monitoring data have been accumulated. Big data brings new opportunities and challenges to radio supervision, one of which is signal retrieval. The task of signal retrieval is to find similar signals for a given segment of signal. In this paper, we propose an idea of FH signal retrieval. Firstly, transform the FH signal into two-dimensional images, and the radio signal retrieval problem is transformed into an image retrieval problem. Then, the advanced achievements in the field of image retrieval can be used to complete signal retrieval. Based on this idea, we propose an FH signal retrieval algorithm named FHSR. In order to extract the signal information better, we also propose a data augmentation algorithm. Experiments show that our method achieves good results in retrieval accuracy and speed, which meets the actual needs.

Masqueraders are a severe insider threat and have become a conventional security issue for most organizations. The majority of existing techniques for detecting masqueraders extract statistical features from file access logs. However, the graph's features from these logs have not been fully explored. In this work, we introduce GSketch. First, it divides each user's file access logs into equal length, non-overlapping time windows. Then file access logs on each time window are transformed into a graph according to chronological order. GSketch extracts global features and local features from the graph. Global features provide a panoramic view of the graph, and local features mine small, induced sub-graphs. Finally, GSketch applies an abnormal detection algorithm to find anomalous points in the feature space and marks these points as masquerader's activities. The effectiveness of GSketch is demonstrated by its excellent performances on two public datasets - WUIL and TWOS.

Recently, high profile data breach incidents have highlighted the importance of insider Intellectual Property(IP) theft research. Matching the patterns of known attack (filtering-based or rule-based) and finding the deviation from normal behavior (anomaly-based) are two typical approaches to prevent insiders from stealing sensitive information. On the one hand, filtering-based or rule-based solutions provide accurate identification of known attacks, and thus they are suitable for IP theft prevention, but they cannot handle the insiders with in-depth knowledge of the protective measures. On the other hand, anomaly-based solutions can find unknown attacks but typically have a high false-positive rate, which limits their applicability to practice. Nowadays, more and more researchers believe that the insider attack could be improved when combining known attack pattern matching with anomaly detection technologies. Therefore, in this paper, we introduce a Data-level Hybrid Framework, dubbed as Terminator, which enabling both detection and prevention. Terminator integrates a prevention module with an anomaly detection module and uses feedback to improve the module for detection or prevention. Different from previous anomaly-based methods that could only detect anomalous activities, Terminator could detect the stealing actions proactively and take real-time actions on these actions. The effectiveness of Terminator is demonstrated by its excellent performances on a collected dataset, involving detailed information in a real-world insider network and attack data simulated by impersonating the genuine users.

Triangle counting (TC) is a fundamental problem in graph analysis and has found numerous applications, which motivates many TC acceleration solutions in the traditional computing platforms like GPU and FPGA. However, these approaches suffer from the bandwidth bottleneck because TC calculation involves a large amount of data transfers. In this paper, we propose to overcome this challenge by designing a TC accelerator utilizing the emerging processing-in-MRAM (PIM) architecture. The true innovation behind our approach is a novel method to perform TC with bitwise logic operations (such as AND), instead of the traditional approaches such as matrix computations. This enables the efficient in-memory implementations of TC computation, which we demonstrate in this paper with computational Spin-Transfer Torque Magnetic RAM (STT-MRAM) arrays. Furthermore, we develop customized graph slicing and mapping techniques to speed up the computation and reduce the energy consumption. We use a device-to-architecture co-simulation framework to validate our proposed TC accelerator. The results show that our data mapping strategy could reduce 99.99% of the computation and 72% of the memory WRITE operations. Compared with the existing GPU or FPGA accelerators, our in-memory accelerator achieves speedups of 9× and 23.4×, respectively, and a 20.6× energy efficiency improvement over the FPGA accelerator.