arXiv subjects

Kai Ma

Publications and source records attributed to Kai Ma.

At least 55 records · Page 3Linked to original sources

arXiv2024

Testing Bell inequality through $h\toττ$ at CEPC

The decay of Higgs boson into two spin-1/2 particles provides an ideal system to reveal quantum entanglement and Bell-nonlocality. Future $e^+e^-$ colliders can improve the measurement accuracy of the spin correlation of tau lepton pairs from Higgs boson decay. We show the testability of Bell inequality through $h\to ττ$ at Circular Electron Positron Collider (CEPC). Two realistic methods of testing Bell inequality are investigated, i.e., Törnqvist's method and Clauser-Home-Shimony-Holt (CHSH) inequality. In the simulation, we take into account the detector effects of CEPC including uncertainties for tracks and jets from $Z$ boson in the production of $e^+e^-\to Zh$. Necessary reconstruction approaches are described to measure quantum entanglement between $τ^+$ and $τ^-$. Finally, we show the sensitivity of CEPC to the Bell inequality violation for the two methods.

hep-ph↗

arXiv2024

QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge

Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT; various organs such as the brain, prostate, kidney, and pancreas; and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks.

eess.IV↗

arXiv2024

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning

Transformer has shown promise in reinforcement learning to model time-varying features for obtaining generalized low-level robot policies on diverse robotics datasets in embodied learning. However, it still suffers from the issues of low data efficiency and high inference latency. In this paper, we propose to investigate the task from a new perspective of the frequency domain. We first observe that the energy density in the frequency domain of a robot's trajectory is mainly concentrated in the low-frequency part. Then, we present the Fourier Controller Network (FCNet), a new network that uses Short-Time Fourier Transform (STFT) to extract and encode time-varying features through frequency domain interpolation. In order to do real-time decision-making, we further adopt FFT and Sliding DFT methods in the model architecture to achieve parallel training and efficient recurrent inference. Extensive results in both simulated (e.g., D4RL) and real-world environments (e.g., robot locomotion) demonstrate FCNet's substantial efficiency and effectiveness over existing methods such as Transformer, e.g., FCNet outperforms Transformer on multi-environmental robotics datasets of all types of sizes (from 1.9M to 120M). The project page and code can be found https://thkkk.github.io/fcnet.

cs.LG↗

arXiv2024

LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction

Radiation therapy treatment planning requires balancing the delivery of the target dose while sparing normal tissues, making it a complex process. To streamline the planning process and enhance its quality, there is a growing demand for knowledge-based planning (KBP). Ensemble learning has shown impressive power in various deep learning tasks, and it has great potential to improve the performance of KBP. However, the effectiveness of ensemble learning heavily depends on the diversity and individual accuracy of the base learners. Moreover, the complexity of model ensembles is a major concern, as it requires maintaining multiple models during inference, leading to increased computational cost and storage overhead. In this study, we propose a novel learning-based ensemble approach named LENAS, which integrates neural architecture search with knowledge distillation for 3D radiotherapy dose prediction. Our approach starts by exhaustively searching each block from an enormous architecture space to identify multiple architectures that exhibit promising performance and significant diversity. To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network. Furthermore, to preserve high-level semantic information, we design a hybrid-loss to optimize the student network, enabling it to recover the knowledge embedded within the teacher networks. The proposed method has been evaluated on two public datasets, OpenKBP and AIMIS. Extensive experimental results demonstrate the effectiveness of our method and its superior performance to the state-of-the-art methods.

eess.IV↗

arXiv2024

The Devil Behind the Mirror: Tracking the Campaigns of Cryptocurrency Abuses on the Dark Web

The dark web has emerged as the state-of-the-art solution for enhanced anonymity. Just like a double-edged sword, it also inadvertently becomes the safety net and breeding ground for illicit activities. Among them, cryptocurrencies have been prevalently abused to receive illicit income while evading regulations. Despite the continuing efforts to combat illicit activities, there is still a lack of an in-depth understanding regarding the characteristics and dynamics of cryptocurrency abuses on the dark web. In this work, we conduct a multi-dimensional and systematic study to track cryptocurrency-related illicit activities and campaigns on the dark web. We first harvest a dataset of 4,923 cryptocurrency-related onion sites with over 130K pages. Then, we detect and extract the illicit blockchain transactions to characterize the cryptocurrency abuses, targeting features from single/clustered addresses and illicit campaigns. Throughout our study, we have identified 2,564 illicit sites with 1,189 illicit blockchain addresses, which account for 90.8 BTC in revenue. Based on their inner connections, we further identify 66 campaigns behind them. Our exploration suggests that illicit activities on the dark web have strong correlations, which can guide us to identify new illicit blockchain addresses and onions, and raise alarms at the early stage of their deployment.

cs.CR↗

arXiv2024

StableDrag: Stable Dragging for Point-based Image Editing

Point-based image editing has attracted remarkable attention since the emergence of DragGAN. Recently, DragDiffusion further pushes forward the generative quality via adapting this dragging technique to diffusion models. Despite these great success, this dragging scheme exhibits two major drawbacks, namely inaccurate point tracking and incomplete motion supervision, which may result in unsatisfactory dragging outcomes. To tackle these issues, we build a stable and precise drag-based editing framework, coined as StableDrag, by designing a discirminative point tracking method and a confidence-based latent enhancement strategy for motion supervision. The former allows us to precisely locate the updated handle points, thereby boosting the stability of long-range manipulation, while the latter is responsible for guaranteeing the optimized latent as high-quality as possible across all the manipulation steps. Thanks to these unique designs, we instantiate two types of image editing models including StableDrag-GAN and StableDrag-Diff, which attains more stable dragging performance, through extensive qualitative experiments and quantitative assessment on DragBench.

cs.CV↗

arXiv2023

Joint Trading and Scheduling among Coupled Carbon-Electricity-Heat-Gas Industrial Clusters

This paper presents a carbon-energy coupling management framework for an industrial park, where the carbon flow model accompanying multi-energy flows is adopted to track and suppress carbon emissions on the user side. To deal with the quadratic constraint of gas flows, a bound tightening algorithm for constraints relaxation is adopted. The synergies among the carbon capture, energy storage, power-to-gas further consume renewable energy and reduce carbon emissions. Aiming at carbon emissions disparities and supply-demand imbalances, this paper proposes a carbon trading ladder reward and punishment mechanism and an energy trading and scheduling method based on Lyapunov optimization and matching game to maximize the long-term benefits of each industrial cluster without knowing the prior information of random variables. Case studies show that our proposed trading method can reduce overall costs and carbon emissions while relieving energy pressure, which is important for Environmental, Social and Governance (ESG).

eess.SY↗

arXiv2023

SoK: On the Security of Non-Fungible Tokens

Non-fungible tokens (NFTs) drive the prosperity of the Web3 ecosystem. By November 2023, the total market value of NFT projects reached approximately 16 billion USD. Accompanying the success of NFTs are various security issues, i.e., attacks and scams are prevalent in the ecosystem. While NFTs have attracted significant attentions from both industry and academia, there is a lack of understanding of kinds of NFT security issues. The discovery, in-depth analysis, and systematic categorization of these security issues are of significant importance for the prosperous development of the NFT ecosystem. To fill the gap, we performed a systematic literature review related to NFT security, and we have identified 142 incidents from 213 security reports and 18 academic papers until October 1st, 2023. Through manual analysis of the compiled security incidents, we have classified them into 12 major categories. Then we explored potential solutions and mitigation strategies. Drawing from these analyses, we established the first NFT security reference frame. Except, we extracted the characteristics of NFT security issues, i.e., the prevalence, severity, and intractability. We have indicated the gap between industry and academy for NFT security, and provide further research directions for the community. This paper, as the first SoK of NFT security, has systematically explored the security issues within the NFT ecosystem, shedding light on their root causes, real-world attacks, and potential ways to address them. Our findings will contribute to the future research of NFT security.

cs.CR↗

arXiv2023

Adversarial Medical Image with Hierarchical Feature Hiding

Deep learning based methods for medical images can be easily compromised by adversarial examples (AEs), posing a great security flaw in clinical decision-making. It has been discovered that conventional adversarial attacks like PGD which optimize the classification logits, are easy to distinguish in the feature space, resulting in accurate reactive defenses. To better understand this phenomenon and reassess the reliability of the reactive defenses for medical AEs, we thoroughly investigate the characteristic of conventional medical AEs. Specifically, we first theoretically prove that conventional adversarial attacks change the outputs by continuously optimizing vulnerable features in a fixed direction, thereby leading to outlier representations in the feature space. Then, a stress test is conducted to reveal the vulnerability of medical images, by comparing with natural images. Interestingly, this vulnerability is a double-edged sword, which can be exploited to hide AEs. We then propose a simple-yet-effective hierarchical feature constraint (HFC), a novel add-on to conventional white-box attacks, which assists to hide the adversarial feature in the target feature distribution. The proposed method is evaluated on three medical datasets, both 2D and 3D, with different modalities. The experimental results demonstrate the superiority of HFC, \emph{i.e.,} it bypasses an array of state-of-the-art adversarial medical AE detectors more efficiently than competing adaptive attacks, which reveals the deficiencies of medical reactive defense and allows to develop more robust defenses in future.

eess.IV↗

arXiv2023

Associated Production of Neutrino and Dark Fermion at Future Lepton Colliders

Fermionic dark matter can be pairly produced and hence searched with missing energy at colliders. We extend such probe to the associated production of a neutrino and a dark sector fermion at the future $e^+ e^-$ colliders such as CEPC, FCC-ee, ILC, and CLIC. Two typical processes, the mono-photon and electron-positron pair productions associated with missing energy, can serve the purpose. While the mono-photon search prevails at CEPC, FCC-ee, and ILC, the $e^+ e^- \met$ channel has more significant contributions at CLIC with much higher collision energy $\sqrt s$. The beam polarizations can help further suppressing the SM backgrounds to enhance the signal significance while differential cross sections can distinguish the Lorentz structure of various effective operators. The combined sensitivity can reach well above $1\tev$ at CEPC/FCC-ee and ILC while it further touches 30\,TeV at CLIC. Comparing with the updated results from the direct detection experiments (XENON1T, PandaX-II, PandaX-4T, LZ, and XENONnT), astrophysical $X/γ$-ray observations, and cosmological constraints for the sub-MeV absorption dark matter, the collider searches are actually more sensitive and hence can provide a complementary approach to addressing the dark fermions.

hep-ph↗

arXiv2023

Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training

Nuclei segmentation is a crucial task for whole slide image analysis in digital pathology. Generally, the segmentation performance of fully-supervised learning heavily depends on the amount and quality of the annotated data. However, it is time-consuming and expensive for professional pathologists to provide accurate pixel-level ground truth, while it is much easier to get coarse labels such as point annotations. In this paper, we propose a weakly-supervised learning method for nuclei segmentation that only requires point annotations for training. First, coarse pixel-level labels are derived from the point annotations based on the Voronoi diagram and the k-means clustering method to avoid overfitting. Second, a co-training strategy with an exponential moving average method is designed to refine the incomplete supervision of the coarse labels. Third, a self-supervised visual representation learning method is tailored for nuclei segmentation of pathology images that transforms the hematoxylin component images into the H&E stained images to gain better understanding of the relationship between the nuclei and cytoplasm. We comprehensively evaluate the proposed method using two public datasets. Both visual and quantitative results demonstrate the superiority of our method to the state-of-the-art methods, and its competitive performance compared to the fully-supervised methods. Code: https://github.com/hust-linyi/SC-Net

eess.IV↗

arXiv2023

Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a memory buffer, have shown good performance in mitigating catastrophic forgetting for previously learned knowledge. However, most of these methods typically treat each new task equally, which may not adequately consider the relationship or similarity between old and new tasks. Furthermore, these methods commonly neglect sample importance in the continual training process and result in sub-optimal performance on certain tasks. To address this challenging problem, we propose Relational Experience Replay (RER), a bi-level learning framework, to adaptively tune task-wise relationships and sample importance within each task to achieve a better `stability' and `plasticity' trade-off. As such, the proposed method is capable of accumulating new knowledge while consolidating previously learned old knowledge during continual learning. Extensive experiments conducted on three publicly available datasets (i.e., CIFAR-10, CIFAR-100, and Tiny ImageNet) show that the proposed method can consistently improve the performance of all baselines and surpass current state-of-the-art methods.

cs.LG↗

arXiv2023

A Deep Dive into NFT Rug Pulls

NFT rug pull is one of the most prominent type of scam that the developers of a project abandon it and then run away with investors' funds. Although they have drawn attention from our community, to the best of our knowledge, the NFT rug pulls have not been systematically explored. To fill the void, this paper presents the first in-depth study of NFT rug pulls. Specifically, we first compile a list of 253 known NFT rug pulls as our initial ground truth, based on which we perform a pilot study, highlighting the key symptoms of NFT rug pulls. Then, we enforce a strict rule-based method to flag more rug pulled NFT projects in the wild, and have labelled 7,487 NFT rug pulls as our extended ground truth. Atop it, we have investigated the art of NFT rug pulls, with kinds of tricks including explicit ones that are embedded with backdoors, and implicit ones that manipulate the market. To release the expansion of the scam, we further design a prediction model to proactively identify the potential rug pull projects in an early stage ahead of the scam happens. We have implemented a prototype system deployed in the real-world setting for over 5 months. Our system has raised alarms for 7,821 NFT projects, by the time of this writing, which can work as a whistle blower that pinpoints rug pull scams timely, thus mitigating the impacts.

cs.CR↗

arXiv2023

A New Perspective to Boost Vision Transformer for Medical Image Classification

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art self-supervised learning approaches.

cs.CV↗

arXiv2022

$α$-cluster decay from $^{24}$Mg resonances produced in $^{12}$C($^{16}$O,$^{24}$Mg)$α$ reaction

A transfer reaction and cluster-decay experiment, $^{12}$C($^{16}$O,$^{24}$Mg$\rightarrow$$α$+$^{20}$Ne)$α$, was performed at a beam energy of 96 MeV. Both recoil and decay $α$ particles were detected in coincidence, allowing us to deduce the energy-momentum of a $^{20}$Ne fragment. A number of resonant states of $^{24}$Mg were reconstructed up to an excitation energy of approximately 30 MeV. Owing to the experimentally achieved excellent resolutions of the $Q$-value and excitation-energy spectra, the relative decay widths for each resonant state in $^{24}$Mg to various final states of $^{20}$Ne were extracted, alone with the total decay width. The obtained results provide good testing ground for theoretical descriptions of the multiple clustering configurations in $^{24}$Mg.

nucl-ex↗

arXiv2022

A Trustworthy Framework for Medical Image Analysis with Deep Learning

Computer vision and machine learning are playing an increasingly important role in computer-assisted diagnosis; however, the application of deep learning to medical imaging has challenges in data availability and data imbalance, and it is especially important that models for medical imaging are built to be trustworthy. Therefore, we propose TRUDLMIA, a trustworthy deep learning framework for medical image analysis, which adopts a modular design, leverages self-supervised pre-training, and utilizes a novel surrogate loss function. Experimental evaluations indicate that models generated from the framework are both trustworthy and high-performing. It is anticipated that the framework will support researchers and clinicians in advancing the use of deep learning for dealing with public health crises including COVID-19.

eess.IV↗

arXiv2022

Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression

Automated methods for Cobb angle estimation are of high demand for scoliosis assessment. Existing methods typically calculate the Cobb angle from landmark estimation, or simply combine the low-level task (e.g., landmark detection and spine segmentation) with the Cobb angle regression task, without fully exploring the benefits from each other. In this study, we propose a novel multi-task framework, named Seg4Reg+, which jointly optimizes the segmentation and regression networks. We thoroughly investigate both local and global consistency and knowledge transfer between each other. Specifically, we propose an attention regularization module leveraging class activation maps (CAMs) from image-segmentation pairs to discover additional supervision in the regression network, and the CAMs can serve as a region-of-interest enhancement gate to facilitate the segmentation task in turn. Meanwhile, we design a novel triangle consistency learning to train the two networks jointly for global optimization. The evaluations performed on the public AASCE Challenge dataset demonstrate the effectiveness of each module and superior performance of our model to the state-of-the-art methods.

cs.CV↗

arXiv2022

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

Building AI models with trustworthiness is important especially in regulated areas such as healthcare. In tackling COVID-19, previous work uses convolutional neural networks as the backbone architecture, which has shown to be prone to over-caution and overconfidence in making decisions, rendering them less trustworthy -- a crucial flaw in the context of medical imaging. In this study, we propose a feature learning approach using Vision Transformers, which use an attention-based mechanism, and examine the representation learning capability of Transformers as a new backbone architecture for medical imaging. Through the task of classifying COVID-19 chest radiographs, we investigate into whether generalization capabilities benefit solely from Vision Transformers' architectural advances. Quantitative and qualitative evaluations are conducted on the trustworthiness of the models, through the use of "trust score" computation and a visual explainability technique. We conclude that the attention-based feature learning approach is promising in building trustworthy deep learning models for healthcare.

eess.IV↗