Search

Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where attackers cause models to misclassify by learning the backdoored features with injected triggers and modified target labels during the training phase. Based on the features of the triggers, these attacks can be categorized into out-of-distribution (OOD) and in-distribution (ID) graph backdoor attacks, triggers with notable differences from the clean sample feature distributions constitute OOD backdoor attacks, whereas the triggers in ID backdoor attacks are nearly identical to the clean sample feature distributions. Existing methods can successfully defend against OOD backdoor attacks by comparing the feature distribution of triggers and clean samples but fail to mitigate stealthy ID backdoor attacks. Due to the lack of proper supervision signals, the main task accuracy is negatively affected in defending against ID backdoor attacks. To bridge this gap, we propose DMGNN against OOD and ID graph backdoor attacks that can powerfully eliminate stealthiness to guarantee defense effectiveness and improve the model performance. Specifically, DMGNN can easily identify the hidden ID and OOD triggers via predicting label transitions based on counterfactual explanation. To further filter the diversity of generated explainable graphs and erase the influence of the trigger features, we present a reverse sampling pruning method to screen and discard the triggers directly on the data level. Extensive experimental evaluations on open graph datasets demonstrate that DMGNN far outperforms the state-of-the-art (SOTA) defense methods, reducing the attack success rate to 5% with almost negligible degradation in model performance (within 3.5%)., Comment: 12 pages, 8 figures

Code Summarization Model (CSM) has been widely used in code production, such as online and web programming for PHP and Javascript. CSMs are essential tools in code production, enhancing software development efficiency and driving innovation in automated code analysis. However, CSMs face risks of exploitation by unauthorized users, particularly in an online environment where CSMs can be easily shared and disseminated. To address these risks, digital watermarks offer a promising solution by embedding imperceptible signatures within the models to assert copyright ownership and track unauthorized usage. Traditional watermarking for CSM copyright protection faces two main challenges: 1) dataset watermarking methods require separate design of triggers and watermark features based on the characteristics of different programming languages, which not only increases the computation complexity but also leads to a lack of generalization, 2) existing watermarks based on code style transformation are easily identifiable by automated detection, demonstrating poor concealment. To tackle these issues, we propose ModMark , a novel model-level digital watermark embedding method. Specifically, by fine-tuning the tokenizer, ModMark achieves cross-language generalization while reducing the complexity of watermark design. Moreover, we employ code noise injection techniques to effectively prevent trigger detection. Experimental results show that our method can achieve 100% watermark verification rate across various programming languages' CSMs, and the concealment and effectiveness of ModMark can also be guaranteed., Comment: 11 pages, 5 figures

Deep learning has emerged as a promising technology for achieving Android malware detection. To further unleash its detection potentials, software visualization can be integrated for analyzing the details of app behaviors clearly. However, facing increasingly sophisticated malware, existing visualization-based methods, analyzing from one or randomly-selected few views, can only detect limited attack types. We propose and implement LensDroid, a novel technique that detects Android malware by visualizing app behaviors from multiple complementary views. Our goal is to harness the power of combining deep learning and software visualization to automatically capture and aggregate high-level features that are not inherently linked, thereby revealing hidden maliciousness of Android app behaviors. To thoroughly comprehend the details of apps, we visualize app behaviors from three related but distinct views of behavioral sensitivities, operational contexts and supported environments. We then extract high-order semantics based on the views accordingly. To exploit semantic complementarity of the views, we design a deep neural network based model for fusing the visualized features from local to global based on their contributions to downstream tasks. A comprehensive comparison with five baseline techniques is performed on datasets of more than 51K apps in three real-world typical scenarios, including overall threats, app evolution and zero-day malware. The experimental results show that the overall performance of LensDroid is better than the baseline techniques. We also validate the complementarity of the views and demonstrate that the multi-view fusion in LensDroid enhances Android malware detection., Comment: Submitted to TIFS

Recent studies have exposed that GNNs are vulnerable to several adversarial attacks, among which backdoor attack is one of the toughest. Similar to Deep Neural Networks (DNNs), backdoor attacks in GNNs lie in the fact that the attacker modifies a portion of graph data by embedding triggers and enforces the model to learn the trigger feature during the model training process. Despite the massive prior backdoor defense works on DNNs, defending against backdoor attacks in GNNs is largely unexplored, severely hindering the widespread application of GNNs in real-world tasks. To bridge this gap, we present GCleaner, the first backdoor mitigation method on GNNs. GCleaner can mitigate the presence of the backdoor logic within backdoored GNNs by reversing the backdoor learning procedure, aiming to restore the model performance to a level similar to that is directly trained on the original clean dataset. To achieve this objective, we ask: How to recover universal and hard backdoor triggers in GNNs? How to unlearn the backdoor trigger feature while maintaining the model performance? We conduct the graph trigger recovery via the explanation method to identify optimal trigger locations, facilitating the search of universal and hard backdoor triggers in the feature space of the backdoored model through maximal similarity. Subsequently, we introduce the backdoor unlearning mechanism, which combines knowledge distillation and gradient-based explainable knowledge for fine-grained backdoor erasure. Extensive experimental evaluations on four benchmark datasets demonstrate that GCleaner can reduce the backdoor attack success rate to 10% with only 1% of clean data, and has almost negligible degradation in model performance, which far outperforms the state-of-the-art (SOTA) defense methods., Comment: 18 pages, 12 figures, 9 tables

Federated Learning (FL), a privacy-preserving decentralized machine learning framework, has been shown to be vulnerable to backdoor attacks. Current research primarily focuses on the Single-Label Backdoor Attack (SBA), wherein adversaries share a consistent target. However, a critical fact is overlooked: adversaries may be non-cooperative, have distinct targets, and operate independently, which exhibits a more practical scenario called Multi-Label Backdoor Attack (MBA). Unfortunately, prior works are ineffective in MBA scenario since non-cooperative attackers exclude each other. In this work, we conduct an in-depth investigation to uncover the inherent constraints of the exclusion: similar backdoor mappings are constructed for different targets, resulting in conflicts among backdoor functions. To address this limitation, we propose Mirage, the first non-cooperative MBA strategy in FL that allows attackers to inject effective and persistent backdoors into the global model without collusion by constructing in-distribution (ID) backdoor mapping. Specifically, we introduce an adversarial adaptation method to bridge the backdoor features and the target distribution in an ID manner. Additionally, we further leverage a constrained optimization method to ensure the ID mapping survives in the global training dynamics. Extensive evaluations demonstrate that Mirage outperforms various state-of-the-art attacks and bypasses existing defenses, achieving an average ASR greater than 97\% and maintaining over 90\% after 900 rounds. This work aims to alert researchers to this potential threat and inspire the design of effective defense mechanisms. Code has been made open-source., Comment: 11 pages, 7 figures

We present Persona-L, a novel approach for creating personas using Large Language Models (LLMs) and an ability-based framework, specifically designed to improve the representation of users with complex needs. Traditional methods of persona creation often fall short of accurately depicting the dynamic and diverse nature of complex needs, resulting in oversimplified or stereotypical profiles. Persona-L enables users to create and interact with personas through a chat interface. Persona-L was evaluated through interviews with UX designers (N=6), where we examined its effectiveness in reflecting the complexities of lived experiences of people with complex needs. We report our findings that indicate the potential of Persona-L to increase empathy and understanding of complex needs while also revealing the need for transparency of data used in persona creation, the role of the language and tone, and the need to provide a more balanced presentation of abilities with constraints.

We investigate the parametrized black hole quasinormal ringdown formalism, which is a robust framework used to analyze quasinormal modes in systems that closely resemble general relativity, paying particular attention to the higher overtones. We find that larger deviations from the general relativity case typically appear in the quasinormal frequencies for the higher overtones. This growing tendency for higher overtones can be understood using an analytical method, and its relations to previous works are briefly discussed. Our findings indicate that we can impose a strong constraint on gravity theories by considering the overtones of quasinormal modes., Comment: v2: minor revisions, accepted for publication in Phys. Rev. D. 34 pages, 12 figures. Data available at https://github.com/JialeZHANG-Phys/pqnm_overtone

The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE). However, due to their black-box nature, these promising AI-driven SE models are still far from being deployed in practice. This lack of explainability poses unwanted risks for their applications in critical tasks, such as vulnerability detection, where decision-making transparency is of paramount importance. This paper endeavors to elucidate this interdisciplinary domain by presenting a systematic literature review of approaches that aim to improve the explainability of AI models within the context of SE. The review canvasses work appearing in the most prominent SE & AI conferences and journals, and spans 63 papers across 21 unique SE tasks. Based on three key Research Questions (RQs), we aim to (1) summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches. Based on our findings, we identified a set of challenges remaining to be addressed in existing studies, together with a roadmap highlighting potential opportunities we deemed appropriate and important for future work., Comment: submitted to ACM Computing Surveys. arXiv admin note: text overlap with arXiv:2202.06840 by other authors

We conducted 4-night multiwavelength observations of an active M-dwarf star EV Lac on 2022 October 24$-$27 with simultaneous coverage of soft X-rays (NICER; 0.2$-$12 $\mathrm{keV}$, Swift XRT; 0.2$-$10 $\mathrm{keV}$), near-ultraviolet (Swift UVOT/UVW2; 1600$-$3500 \r{A}), optical photometry (TESS; 6000$-$10000 \r{A}), and optical spectroscopy (Nayuta/MALLS; 6350$-$6800 \r{A}). During the campaign, we detected a flare starting at 12:28 UTC on October 25 with its white-light bolometric energy of $3.4 \times 10^{32}$ erg. At about 1 hour after this flare peak, our $\mathrm{H\alpha}$ spectrum showed a blue-shifted excess component at its corresponding velocity of $\sim 100 \: \mathrm{km \: s^{-1}}$. This may indicate that the prominence erupted with a 1-hour delay of the flare peak. Furthermore, the simultaneous 20-second cadence near-ultraviolet and white-light curves show gradual and rapid brightening behaviors during the rising phase at this flare. The ratio of flux in NUV to white light at the gradual brightening was $\sim 0.49$, which may suggest that the temperature of the blackbody is low ($< 9000 \: \mathrm{K}$) or the maximum energy flux of a nonthermal electron beam is less than $5\times10^{11} \: \mathrm{erg \: cm^{-2} \: s^{-1}}$. Our simultaneous observations of NUV and white-light flare raise the issue of a simple estimation of UV flux from optical continuum data by using a blackbody model., Comment: 19 pages, 10 figures. Accepted for publication in Publications of the Astronomical Society of Japan

Laparoscopic surgery offers minimally invasive procedures with better patient outcomes, but smoke presence challenges visibility and safety. Existing learning-based methods demand large datasets and high computational resources. We propose the Progressive Frequency-Aware Network (PFAN), a lightweight GAN framework for laparoscopic image desmoking, combining the strengths of CNN and Transformer for progressive information extraction in the frequency domain. PFAN features CNN-based Multi-scale Bottleneck-Inverting (MBI) Blocks for capturing local high-frequency information and Locally-Enhanced Axial Attention Transformers (LAT) for efficiently handling global low-frequency information. PFAN efficiently desmokes laparoscopic images even with limited training data. Our method outperforms state-of-the-art approaches in PSNR, SSIM, CIEDE2000, and visual quality on the Cholec80 dataset and retains only 629K parameters. Our code and models are made publicly available at: https://github.com/jlzcode/PFAN.

Radio bursts from nearby active M-dwarfs have been frequently reported and extensively studied in solar or planetary paradigms. Whereas, their sub-structures or fine structures remain rarely explored despite their potential significance in diagnosing the plasma and magnetic field properties of the star. Such studies in the past have been limited by the sensitivity of radio telescopes. Here we report the inspiring results from the high time-resolution observations of a known flare star AD Leo with the Five-hundred-meter Aperture Spherical radio Telescope (FAST). We detected many radio bursts in the two days of observations with fine structures in the form of numerous millisecond-scale sub-bursts. Sub-bursts on the first day display stripe-like shapes with nearly uniform frequency drift rates, which are possibly stellar analogs to Jovian S-bursts. Sub-bursts on the second day, however, reveal a different blob-like shape with random occurrence patterns and are akin to solar radio spikes. The new observational results suggest that the intense emission from AD Leo is driven by electron cyclotron maser instability which may be related to stellar flares or interactions with a planetary companion., Comment: 25 pages, 12 figures, accepted for publication in ApJ

In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer., Comment: Accepted to ICLR 2024. Code and models are available at https://github.com/gladzhang/Xformer

Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, ie, similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts. We also illustrate the philosophy of our design with an interesting analytical visualization., Comment: Accepted to AAAI 2023 (Oral); 9 pages, 6 figures

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Retractable Transformer (ART) for image restoration, which presents both dense and sparse attention modules in the network. The sparse attention module allows tokens from sparse areas to interact and thus provides a wider receptive field. Furthermore, the alternating application of dense and sparse attention modules greatly enhances representation ability of Transformer while providing retractable attention on the input image.We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks. Experimental results validate that our proposed ART outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually. We also provide code and models at https://github.com/gladzhang/ART., Comment: Accepted to ICLR 2023. Code and models are available at https://github.com/gladzhang/ART

Extreme-ultraviolet late phase (ELP) refers to the second extreme-ultraviolet (EUV) radiation enhancement observed in certain solar flares, which usually occurs tens of minutes to several hours after the peak of soft X-ray emission. The coronal loop system that hosts the ELP emission is often different from the main flaring arcade, and the enhanced EUV emission therein may imply an additional heating process. However, the origin of the ELP remains rather unclear. Here we present the analysis of a C1.4 flare that features such an ELP, which is also observed in microwave wavelengths by the Expanded Owens Valley Solar Array (EOVSA). Similar to the case of the ELP, we find a gradual microwave enhancement that occurs about three minutes after the main impulsive phase microwave peaks. Radio sources coincide with both footpoints of the ELP loops and spectral fits on the time-varying microwave spectra demonstrate a clear deviation of the electron distribution from the Maxwellian case, which could result from injected nonthermal electrons or nonuniform heating to the footpoint plasma. We further point out that the delayed microwave enhancement suggests the presence of an additional heating process, which could be responsible for the evaporation of heated plasma that fills the ELP loops, producing the prolonged ELP emission.