Search

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of adversarial robustness. In this paper, we incorporate the causal inference into the IB framework to alleviate such a problem. Specifically, we divide the features obtained by the IB method into robust features (content information) and non-robust features (style information) via the instrumental variables to estimate the causal effects. With the utilization of such a framework, the influence of non-robust features could be mitigated to strengthen the adversarial robustness. We make an analysis of the effectiveness of our proposed method. The extensive experiments in MNIST, FashionMNIST, and CIFAR-10 show that our method exhibits the considerable robustness against multiple adversarial attacks. Our code would be released.

The nonleptonic decays $B_{d,s} \to K^{*0} {\overline K^{*0}}$ are reanalyzed in perturbative QCD approach, which is based on the $k_{\rm T}$ factorization. In the standard model, the calculated branching fraction and longitudinal polarization fraction of $B_{d} \to K^{*0} {\overline K^{*0}}$ are in agreement with experimental measurements, while the predictions of $B_{s} \to K^{*0} {\overline K^{*0}}$ cannot agree with data simultaneously. The parameter that combines of longitudinal polarization fractions and branching fractions evaluated to be $L_{K^*\overline{K}^{*0}}^{\rm PQCD}= 12.7^{+5.6} _{-3.2}$, which is also larger than that abstracted from experimental measurements. We then study all observables by introducing a family non-universal $Z^{\prime}$ boson in $b\to s q\bar q$ transitions. In order to reduce the number of new parameters, we simplify the model as possible. It is found that with the fixed value $\omega_{B_s}=0.55$, these exists parameter space where all measurements, including the branching fraction, longitudinal polarization fraction and $L_{K^*\overline{K}^{*0}}$-parameter, could be accommodated simultaneously. All our results and the small parameter space could be further tested in the running LHC experiments, Belle-II and future high-energy colliders., Comment: 21 pages, 6 figures

The extraction of contrast-filled vessels from X-ray coronary angiography (XCA) image sequence has important clinical significance for intuitively diagnosis and therapy. In this study, the XCA image sequence is regarded as a 3D tensor input, the vessel layer is regarded as a sparse tensor, and the background layer is regarded as a low-rank tensor. Using tensor nuclear norm (TNN) minimization, a novel method for vessel layer extraction based on tensor robust principal component analysis (TRPCA) is proposed. Furthermore, considering the irregular movement of vessels and the low-frequency dynamic disturbance of surrounding irrelevant tissues, the total variation (TV) regularized spatial-temporal constraint is introduced to smooth the foreground layer. Subsequently, for vessel layer images with uneven contrast distribution, a two-stage region growing (TSRG) method is utilized for vessel enhancement and segmentation. A global threshold method is used as the preprocessing to obtain main branches, and the Radon-Like features (RLF) filter is used to enhance and connect broken minor segments, the final binary vessel mask is constructed by combining the two intermediate results. The visibility of TV-TRPCA algorithm for foreground extraction is evaluated on clinical XCA image sequences and third-party dataset, which can effectively improve the performance of commonly used vessel segmentation algorithms. Based on TV-TRPCA, the accuracy of TSRG algorithm for vessel segmentation is further evaluated. Both qualitative and quantitative results validate the superiority of the proposed method over existing state-of-the-art approaches., Comment: 34pages, 14figures, 5tables

Motivated by the problem of global stability of thermodynamical equilibria in non-equilibrium thermodynamics formulated in a recent paper [12], we introduce some mechanisms for constructing semi-infinite orbits of contact Hamiltonian systems connecting two Legendrian graphs from the viewpoint of Aubry-Mather theory and weak KAM theory., Comment: 25 pages, 1 figure, communications and comments are welcome!

Code review is one of the best practices as a powerful safeguard for software quality. In practice, senior or highly skilled reviewers inspect source code and provide constructive comments, considering what authors may ignore, for example, some special cases. The collaborative validation between contributors results in code being highly qualified and less chance of bugs. However, since personal knowledge is limited and varies, the efficiency and effectiveness of code review practice are worthy of further improvement. In fact, it still takes a colossal and time-consuming effort to deliver useful review comments. This paper explores a synergy of multiple practical review comments to enhance code review and proposes AUGER (AUtomatically GEnerating Review comments): a review comments generator with pre-training models. We first collect empirical review data from 11 notable Java projects and construct a dataset of 10,882 code changes. By leveraging Text-to-Text Transfer Transformer (T5) models, the framework synthesizes valuable knowledge in the training stage and effectively outperforms baselines by 37.38% in ROUGE-L. 29% of our automatic review comments are considered useful according to prior studies. The inference generates just in 20 seconds and is also open to training further. Moreover, the performance also gets improved when thoroughly analyzed in case study., Comment: Accepted by ESEC/FSE-2022

Accurate modeling of spatial dependence is pivotal in analyzing spatial data, influencing parameter estimation and out-of-sample predictions. The spatial structure and geometry of the data significantly impact valid statistical inference. Existing models for areal data often rely on adjacency matrices, struggling to differentiate between polygons of varying sizes and shapes. Conversely, data fusion models, while effective, rely on computationally intensive numerical integrals, presenting challenges for moderately large datasets. In response to these issues, we propose the Hausdorff-Gaussian process (HGP), a versatile model class utilizing the Hausdorff distance to capture spatial dependence in both point and areal data. We introduce a valid correlation function within the HGP framework, accommodating diverse modeling techniques, including geostatistical and areal models. Integration into generalized linear mixed-effects models enhances its applicability, particularly in addressing change of support and data fusion challenges. We validate our approach through a comprehensive simulation study and application to two real-world scenarios: one involving areal data and another demonstrating its effectiveness in data fusion. The results suggest that the HGP is competitive with specialized models regarding goodness-of-fit and prediction performances. In summary, the HGP offers a flexible and robust solution for modeling spatial data of various types and shapes, with potential applications spanning fields such as public health and climate science.

Modern Python projects execute computational functions using native libraries and give Python interfaces to boost execution speed; hence, testing these libraries becomes critical to the project's robustness. One challenge is that existing approaches use coverage to guide generation, but native libraries run as black boxes to Python code with no execution information. Another is that dynamic binary instrumentation reduces testing performance as it needs to monitor both native libraries and the Python virtual machine. To address these challenges, in this paper, we propose an automated test case generation approach that works at the Python code layer. Our insight is that many path conditions in native libraries are for processing input data structures through interacting with the VM. In our approach, we instrument the Python Interpreter to monitor the interactions between native libraries and VM, derive constraints on the structures, and then use the constraints to guide test case generation. We implement our approach in a tool named PyCing and apply it to six widely-used Python projects. The experimental results reveal that with the structure constraint guidance, PyCing can cover more execution paths than existing test cases and state-of-the-art tools. Also, with the checkers in the testing framework Pytest, PyCing can identify segmentation faults in 10 Python interfaces and memory leaks in 9. Our instrumentation strategy also has an acceptable influence on testing efficiency., Comment: 11 panges

In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL). In contrast to previous works in this direction, we employ a server-side approximation for the Quasi-Newton method without requiring any training data from the clients. In this way, we not only shift the computation burden from clients to server, but also eliminate the additional communication for second-order updates between clients and server entirely. We provide theoretical guarantee for convergence of our novel method, and empirically demonstrate our fast convergence and communication savings in both convex and non-convex settings.

Adversarial training methods are state-of-the-art (SOTA) empirical defense methods against adversarial examples. Many regularization methods have been proven to be effective with the combination of adversarial training. Nevertheless, such regularization methods are implemented in the time domain. Since adversarial vulnerability can be regarded as a high-frequency phenomenon, it is essential to regulate the adversarially-trained neural network models in the frequency domain. Faced with these challenges, we make a theoretical analysis on the regularization property of wavelets which can enhance adversarial training. We propose a wavelet regularization method based on the Haar wavelet decomposition which is named Wavelet Average Pooling. This wavelet regularization module is integrated into the wide residual neural network so that a new WideWaveletResNet model is formed. On the datasets of CIFAR-10 and CIFAR-100, our proposed Adversarial Wavelet Training method realizes considerable robustness under different types of attacks. It verifies the assumption that our wavelet regularization method can enhance adversarial robustness especially in the deep wide neural networks. The visualization experiments of the Frequency Principle (F-Principle) and interpretability are implemented to show the effectiveness of our method. A detailed comparison based on different wavelet base functions is presented. The code is available at the repository: \url{https://github.com/momo1986/AdversarialWaveletTraining}., Comment: Preprint version

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g., containing a keyword) to be predicted as a target label of the adversary's choice. In this paper, we demonstrate that it is possible to design a backdoor attack that is both stealthy (i.e., hard to notice) and effective (i.e., has a high attack success rate). We propose BITE, a backdoor attack that poisons the training data to establish strong correlations between the target label and a set of "trigger words". These trigger words are iteratively identified and injected into the target-label instances through natural word-level perturbations. The poisoned training data instruct the victim model to predict the target label on inputs containing trigger words, forming the backdoor. Experiments on four text classification datasets show that our proposed attack is significantly more effective than baseline methods while maintaining decent stealthiness, raising alarm on the usage of untrusted training data. We further propose a defense method named DeBITE based on potential trigger word removal, which outperforms existing methods in defending against BITE and generalizes well to handling other backdoor attacks., Comment: Accepted to ACL 2023

In this paper, we investigate the medium modifications of $p_{T}$ dispersion($p_{T}D$) of inclusive jets with small radius ($R=0.2$) in Pb+Pb collisions at $\sqrt{s}=2.76$~TeV. The partonic spectrum in the initial hard scattering of elementary collisions are obtained by an event generator POWHEG+PYTHIA, which matches the next-to-leading (NLO) matrix elements with parton showering, and energy loss of fast parton traversing in hot/dense QCD medium is calculated by Monte Carlo simulation within Higher-Twist formalism of jet quenching in heavy-ion collisions. We present the model calculations of normalized $p_{T}D$ distributions for inclusive jets in p+p and Pb+Pb collisions at $\sqrt{s}=2.76$~TeV, which give nice descriptions of ALICE measurements. It is shown that the $p_{T}D$ distributions of inclusive jets in Pb+Pb are shifted to higher $p_{T}D$ region relative to that in p+p. Thus the nuclear modification factor of $p_{T}D$ distributions for inclusive jets is smaller than unity at small $p_{T}D$ region, while larger than one at large $p_{T}D$ region. This behaviour results from more uneven $p_T$ of jet constituents as well as the fraction alteration of gluon/quark initiated jets in heavy-ion collisions. The difference of $p_{T}D$ distributions between groomed and ungroomed jets in Pb+Pb collisions are also discussed.

Non-fullerene acceptors (NFAs) are excellent light harvesters, yet the origin of such high optical extinction is not well understood. In this work, we investigate the absorption strength of NFAs by building a database of time-dependent density functional theory (TDDFT) calculations of ~500 pi-conjugated molecules. The calculations are first validated by comparison with experimental measurements on liquid and solid state using common fullerene and non-fullerene acceptors. We find that the molar extinction coefficient ({\epsilon}_(d,max)) shows reasonable agreement between calculation in vacuum and experiment for molecules in solution, highlighting the effectiveness of TDDFT for predicting optical properties of organic pi-conjugated molecules. We then perform a statistical analysis based on molecular descriptors to identify which features are important in defining the absorption strength. This allows us to identify structural features that are correlated with high absorption strength in NFAs and could be used to guide molecular design: highly absorbing NFAs should possess a planar, linear, and fully conjugated molecular backbone with highly polarisable heteroatoms. We then exploit a random decision forest to draw predictions for {\epsilon}_(d,max) using a computational framework based on extended tight-binding Hamiltonians, which shows reasonable predicting accuracy with lower computational cost than TDDFT. This work provides a general understanding of the relationship between molecular structure and absorption strength in pi-conjugated organic molecules, including NFAs, while introducing predictive machine-learning models of low computational cost., Comment: 40 pages and 5 figures (main text)