arXiv subjects

Jingyi Wang

Publications and source records attributed to Jingyi Wang.

At least 127 records · Page 7Linked to original sources

arXiv2022

An Optimization algorithm for nonsmooth nonconvex problems with upper-C^2 objective

An optimization algorithm for nonsmooth nonconvex constrained optimization problems with upper-C2 objective functions is proposed and analyzed. Upper-C2 is a weakly concave property that exists in difference of convex (DC) functions and arises naturally in many applications, particularly certain classes of solutions to parametric optimization problems [34, 4], e.g., recourse of stochastic programming [36] and projection into closed sets [34]. The algorithm can be viewed as a bundle method specialized for upper-C2 problems and is globally convergent with bounded algorithm parameters. Compared to conventional bundle methods, the proposed method is both simpler and computationally more efficient. The algorithm handles general smooth constraints similarly to sequential quadratic programming (SQP) methods and uses a line search to ensure progress. The potential inconsistencies from the linearization of the constraints are addressed through a penalty method. The capabilities of the algorithm are demonstrated by solving both simple upper-C2 problems and real-world optimal power flow problems used in current power grid industry practices.

math.OC↗

arXiv2022

A simplified nonsmooth nonconvex bundle method with applications to security-constrained ACOPF problems

An optimization algorithm for a group of nonsmooth nonconvex problems inspired by two-stage stochastic programming problems is proposed. The main challenges for these problems include (1) the problems lack the popular lower-type properties such as prox-regularity assumed in many nonsmooth nonconvex optimization algorithms, (2) the objective can not be analytically expressed and (3) the evaluation of function values and subgradients are computationally expensive. To address these challenges, this report first examines the properties that exist in many two-stage problems, specifically upper-C^2 objectives. Then, we show that quadratic penalty method for security-constrained alternating current optimal power flow (SCACOPF) contingency problems can make the contingency solution functions upper-C^2 . Based on these observations, a simplified bundle algorithm that bears similarity to sequential quadratic programming (SQP) method is proposed. It is more efficient in implementation and computation compared to conventional bundle methods. Global convergence analysis of the algorithm is presented under novel and reasonable assumptions. The proposed algorithm therefore fills the gap of theoretical convergence for some smoothed SCACOPF problems. The inconsistency that might arise in our treatment of the constraints are addressed through a penalty algorithm whose convergence analysis is also provided. Finally, theoretical capabilities and numerical performance of the algorithm are demonstrated through numerical examples.

math.OC↗

arXiv2021

Repairing Adversarial Texts through Perturbation

It is known that neural networks are subject to attacks through adversarial perturbations, i.e., inputs which are maliciously crafted through perturbations to induce wrong predictions. Furthermore, such attacks are impossible to eliminate, i.e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training. Multiple approaches have been developed to detect and reject such adversarial inputs, mostly in the image domain. Rejecting suspicious inputs however may not be always feasible or ideal. First, normal inputs may be rejected due to false alarms generated by the detection algorithm. Second, denial-of-service attacks may be conducted by feeding such systems with adversarial inputs. To address the gap, in this work, we propose an approach to automatically repair adversarial texts at runtime. Given a text which is suspected to be adversarial, we novelly apply multiple adversarial perturbation methods in a positive way to identify a repair, i.e., a slightly mutated but semantically equivalent text that the neural network correctly classifies. Our approach has been experimented with multiple models trained for natural language processing tasks and the results show that our approach is effective, i.e., it successfully repairs about 80\% of the adversarial texts. Furthermore, depending on the applied perturbation method, an adversarial text could be repaired in as short as one second on average.

cs.CL↗

arXiv2021

NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification

Deep neural networks (DNNs) have demonstrated their outperformance in various domains. However, it raises a social concern whether DNNs can produce reliable and fair decisions especially when they are applied to sensitive domains involving valuable resource allocation, such as education, loan, and employment. It is crucial to conduct fairness testing before DNNs are reliably deployed to such sensitive domains, i.e., generating as many instances as possible to uncover fairness violations. However, the existing testing methods are still limited from three aspects: interpretability, performance, and generalizability. To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data. Extensive evaluations across 7 datasets and the corresponding DNNs demonstrate NeuronFair's superior performance. For instance, on structured datasets, it generates much more instances (~x5.84) and saves more time (with an average speedup of 534.56%) compared with the state-of-the-art methods. Besides, the instances of NeuronFair can also be leveraged to improve the fairness of the biased DNNs, which helps build more fair and trustworthy deep learning systems.

cs.LG↗

arXiv2021

Better Pay Attention Whilst Fuzzing

Fuzzing is one of the prevailing methods for vulnerability detection. However, even state-of-the-art fuzzing methods become ineffective after some period of time, i.e., the coverage hardly improves as existing methods are ineffective to focus the attention of fuzzing on covering the hard-to-trigger program paths. In other words, they cannot generate inputs that can break the bottleneck due to the fundamental difficulty in capturing the complex relations between the test inputs and program coverage. In particular, existing fuzzers suffer from the following main limitations: 1) lacking an overall analysis of the program to identify the most "rewarding" seeds, and 2) lacking an effective mutation strategy which could continuously select and mutates the more relevant "bytes" of the seeds. In this work, we propose an approach called ATTuzz to address these two issues systematically. First, we propose a lightweight dynamic analysis technique which estimates the "reward" of covering each basic block and selects the most rewarding seeds accordingly. Second, we mutate the selected seeds according to a neural network model which predicts whether a certain "rewarding" block will be covered given certain mutation on certain bytes of a seed. The model is a deep learning model equipped with attention mechanism which is learned and updated periodically whilst fuzzing. Our evaluation shows that ATTuzz significantly outperforms 5 state-of-the-art grey-box fuzzers on 13 popular real-world programs at achieving higher edge coverage and finding new bugs. In particular, ATTuzz achieved 2X edge coverage and 4X bugs detected than AFL over 24-hour runs. Moreover, ATTuzz persistently improves the edge coverage in the long run, i.e., achieving 50% more coverage than AFL in 5 days.

cs.CR↗

arXiv2021

Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models

Deep learning (DL) models, especially those large-scale and high-performance ones, can be very costly to train, demanding a great amount of data and computational resources. Unauthorized reproduction of DL models can lead to copyright infringement and cause huge economic losses to model owners. Existing copyright protection techniques are mostly based on watermarking, which embeds an owner-specified watermark into the model. While being able to provide exact ownership verification, these techniques are 1) invasive, as they need to tamper with the training process, which may affect the utility or introduce new security risks; 2) prone to adaptive attacks that attempt to remove the watermark; and 3) not robust to the emerging model extraction attacks. Latest fingerprinting work, though being non-invasive, also falls short when facing the diverse and ever-growing attack scenarios. In this paper, we propose a novel testing framework for DL copyright protection: DEEPJUDGE. DEEPJUDGE quantitatively tests the similarities between two DL models: a victim model and a suspect model. It leverages a diverse set of testing metrics and test case generation methods to produce a chain of supporting evidence to help determine whether a suspect model is a copy of the victim model. Advantages of DEEPJUDGE include: 1) non-invasive, as it works directly on the model and does not tamper with the training process; 2) efficient, as it only needs a small set of test cases and a quick scan of models; 3) flexible, as it can easily incorporate new metrics or generation methods to obtain more confident judgement; and 4) fairly robust to model extraction and adaptive attacks. We verify the effectiveness of DEEPJUDGE under typical copyright infringement scenarios, including model finetuning, pruning and extraction, via extensive experiments on both image and speech datasets with a variety of model architectures.

cs.CR↗

arXiv2021

Fairness Testing of Deep Image Classification with Adequacy Metrics

As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these applications before deployment. Existing fairness testing methods suffer from the following limitations: 1) applicability, i.e., they are only applicable for structured data or text without handling the high-dimensional and abstract domain sampling in the semantic level for image classification applications; 2) functionality, i.e., they generate unfair samples without providing testing criterion to characterize the model's fairness adequacy. To fill the gap, we propose DeepFAIT, a systematic fairness testing framework specifically designed for deep image classification applications. DeepFAIT consists of several important components enabling effective fairness testing of deep image classification applications: 1) a neuron selection strategy to identify the fairness-related neurons; 2) a set of multi-granularity adequacy metrics to evaluate the model's fairness; 3) a test selection algorithm for fixing the fairness issues efficiently. We have conducted experiments on widely adopted large-scale face recognition applications, i.e., VGGFace and FairFace. The experimental results confirm that our approach can effectively identify the fairness-related neurons, characterize the model's fairness, and select the most valuable test cases to mitigate the model's fairness issues.

cs.LG↗

arXiv2021

On measuring the Hubble constant with X-ray reverberation mapping of active galactic nuclei

We show that X-ray reverberation mapping can be used to measure the distance to type 1 active galactic nuclei (AGNs). This is because X-ray photons originally emitted from the `corona' close to the black hole irradiate the accretion disc and are re-emitted with a characteristic `reflection' spectrum that includes a prominent $\sim 6.4$ keV iron emission line. The shape of the reflection spectrum depends on the irradiating flux, and the light-crossing delay between continuum photons observed directly from the corona and the reflected photons constrains the size of the disc. Simultaneously modelling the X-ray spectrum and the time delays between photons of different energies therefore constrains the intrinsic reflected luminosity, and the distance follows from the observed reflected flux. Alternatively, the distance can be measured from the X-ray spectrum alone if the black hole mass is known. We develop a new model of our RELTRANS X-ray reverberation mapping package, called RTDIST, that has distance as a model parameter. We simulate a synthetic observation that we fit with our new model, and find that this technique applied to a sample of $\sim 25$ AGNs can be used to measure the Hubble constant with a $3 σ$ statistical uncertainty of $\sim 6~{\rm km}~{\rm s}^{-1}{\rm Mpc}^{-1}$. Since the technique is completely independent of the traditional distance ladder and the cosmic microwave background radiation, it has the potential to address the current tension between them. We discuss sources of modelling uncertainty, and how they can be addressed in the near future.

astro-ph.HE↗

arXiv2021

Stabilization of continuous-time Markov/semi-Markov jump linear systems via finite data-rate feedback

This paper investigates almost sure exponential stabilization of continuous-time Markov jump linear systems (MJLSs) under communication data-rate constraints by introducing sampling and quantization into the feedback control. Different from previous works, the sampling times and the jump times are independent of each other in this paper. The quantization is recursively adjusted on the sampling time, and its updating strategy does not depend on the switching in a sampling interval. In other words, the explicit value of the switching signal in a sampling interval is not necessary. The numerically testable condition is developed to ensure almost sure exponential stabilization of MJLSs under the proposed communication and control protocols. We also drop the assumption of stabilizability of all individual modes required in previous works about the switched systems. Moreover, we extend the result to the case of continuous-time semi-Markov jump linear systems (semi-MJLSs) via the semi-Markov kernel approach. Finally, some numerical examples are presented to illustrate the effectiveness of the proposed communication and control protocols.

math.DS↗

arXiv2021

EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography

As an important scan plane, four chamber view is routinely performed in both second trimester perinatal screening and fetal echocardiographic examinations. The biometrics in this plane including cardio-thoracic ratio (CTR) and cardiac axis are usually measured by sonographers for diagnosing congenital heart disease. However, due to the commonly existing artifacts like acoustic shadowing, the traditional manual measurements not only suffer from the low efficiency, but also with the inconsistent results depending on the operators' skills. In this paper, we present an anchor-free ellipse detection network, namely EllipseNet, which detects the cardiac and thoracic regions in ellipse and automatically calculates the CTR and cardiac axis for fetal cardiac biometrics in 4-chamber view. In particular, we formulate the network that detects the center of each object as points and regresses the ellipses' parameters simultaneously. We define an intersection-over-union loss to further regulate the regression procedure. We evaluate EllipseNet on clinical echocardiogram dataset with more than 2000 subjects. Experimental results show that the proposed framework outperforms several state-of-the-art methods. Source code will be available at https://git.openi.org.cn/capepoint/EllipseNet .

eess.IV↗

arXiv2021

Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model's fairness. Existing fairness testing approaches however have two major limitations. Firstly, they only work well on traditional machine learning models and have poor performance (e.g., effectiveness and efficiency) on deep learning models. Secondly, they only work on simple structured (e.g., tabular) data and are not applicable for domains such as text. In this work, we bridge the gap by proposing a scalable and effective approach for systematically searching for discriminatory samples while extending existing fairness testing approaches to address a more challenging domain, i.e., text classification. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which is significantly more scalable and effective. Experimental results show that on average, our approach explores the search space much more effectively (9.62 and 2.38 times more than the state-of-the-art methods respectively on tabular and text datasets) and generates much more discriminatory samples (24.95 and 2.68 times) within a same reasonable time. Moreover, the retrained models reduce discrimination by 57.2% and 60.2% respectively on average.

cs.LG↗

arXiv2021

Modelling correlated variability in accreting black holes: the effect of high density and variable ionisation on reverberation lags

We present a new release of the RELTRANS model to fit the complex cross-spectrum of accreting black holes as a function of energy. The model accounts for continuum lags and reverberation lags self-consistently in order to consider the widest possible range of X-ray variability timescales. We introduce a more self-consistent treatment of the reverberation lags, accounting for how the time variations of the illuminating flux change the ionisation level of the accretion disc. This process varies the shape of the reflection spectrum in time causing an additional source of lags besides the light crossing delay. We also consider electron densities in the accretion disc up to $10^{20}$ cm$^{-3}$, which are found in most of the stellar mass black holes and in some AGN. These high densities increase the amplitude of the reverberation lags below $1$ keV since the reflection flux enhances in the same energy range. In addition, we investigate the properties of hard lags produced by variations in the power-law index of the continuum spectrum, which can be interpreted as due to roughly $3\%$ variability in the corona's optical depth and temperature. As a test case, we simultaneously fit the lag energy spectra in a wide range of Fourier frequency for the black hole candidate MAXI J1820+070 observed with NICER. The best fit shows how the reverberation lags contribute even at the longer timescales where the hard lags are important. This proves the importance of modelling these two lags together and self-consistently in order to constrain the parameters of the system.

astro-ph.HE↗

arXiv2021

Adversarial Attacks and Mitigation for Anomaly Detectors of Cyber-Physical Systems

The threats faced by cyber-physical systems (CPSs) in critical infrastructure have motivated research into a multitude of attack detection mechanisms, including anomaly detectors based on neural network models. The effectiveness of anomaly detectors can be assessed by subjecting them to test suites of attacks, but less consideration has been given to adversarial attackers that craft noise specifically designed to deceive them. While successfully applied in domains such as images and audio, adversarial attacks are much harder to implement in CPSs due to the presence of other built-in defence mechanisms such as rule checkers(or invariant checkers). In this work, we present an adversarial attack that simultaneously evades the anomaly detectors and rule checkers of a CPS. Inspired by existing gradient-based approaches, our adversarial attack crafts noise over the sensor and actuator values, then uses a genetic algorithm to optimise the latter, ensuring that the neural network and the rule checking system are both deceived.We implemented our approach for two real-world critical infrastructure testbeds, successfully reducing the classification accuracy of their detectors by over 50% on average, while simultaneously avoiding detection by rule checkers. Finally, we explore whether these attacks can be mitigated by training the detectors on adversarial samples.

cs.CR↗

arXiv2021

Towards Repairing Neural Networks Correctly

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification techniques have been proposed to tackle the correctness problem of neural networks, it is possible that static verification may never be sufficiently scalable to handle real-world neural networks. In this work, we propose a runtime verification method to ensure the correctness of neural networks. Given a neural network and a desirable safety property, we adopt state-of-the-art static verification techniques to identify strategically locations to introduce additional gates which "correct" neural network behaviors at runtime. Experiment results show that our approach effectively generates neural networks which are guaranteed to satisfy the properties, whilst being consistent with the original neural network most of the time.

cs.LG↗

arXiv2021

An Anomaly Event Detection Method Based on GNN Algorithm for Multi-data Sources

Anomaly event detection is crucial for critical infrastructure security(transportation system, social-ecological sector, insurance service, government sector etc.) due to its ability to reveal and address the potential cyber-threats in advance by analysing the data(messages, microblogs, logs etc.) from digital systems and networks. However, the convenience and applicability of smart devices and the maturity of connected technology make the social anomaly events data multi-source and dynamic, which result in the inadaptability for multi-source data detection and thus affect the critical infrastructure security. To effectively address the proposed problems, in this paper, we design a novel anomaly detection method based on multi-source data. First, we leverage spectral clustering algorithm for feature extraction and fusion of multiple data sources. Second, by harnessing the power of deep graph neural network(Deep-GNN), we perform a fine-gained anomaly social event detection, revealing the threatening events and guarantee the critical infrastructure security. Experimental results demonstrate that our framework outperforms other baseline anomaly event detection methods and shows high tracking accuracy, strong robustness and stability.

cs.SI↗

arXiv2021

Attack as Defense: Characterizing Adversarial Examples using Robustness

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have been proposed to improve robustness of deep learning software, many of them are ineffective against adaptive attacks. In this work, we propose a novel characterization to distinguish adversarial examples from benign ones based on the observation that adversarial examples are significantly less robust than benign ones. As existing robustness measurement does not scale to large networks, we propose a novel defense framework, named attack as defense (A2D), to detect adversarial examples by effectively evaluating an example's robustness. A2D uses the cost of attacking an input for robustness evaluation and identifies those less robust examples as adversarial since less robust examples are easier to attack. Extensive experiment results on MNIST, CIFAR10 and ImageNet show that A2D is more effective than recent promising approaches. We also evaluate our defence against potential adaptive attacks and show that A2D is effective in defending carefully designed adaptive attacks, e.g., the attack success rate drops to 0% on CIFAR10.

cs.CR↗

arXiv2021

Disk, Corona, Jet Connection in the Intermediate State of MAXI J1820+070 Revealed by NICER Spectral-Timing Analysis

We analyze 5 epochs of NICER data of the black hole X-ray binary MAXI J1820+070 during the bright hard-to-soft state transition in its 2018 outburst with both reflection spectroscopy and Fourier-resolved timing analysis. We confirm the previous discovery of reverberation lags in the hard state, and find that the frequency range where the (soft) reverberation lag dominates decreases with the reverberation lag amplitude increasing during the transition, suggesting an increasing X-ray emitting region, possibly due to an expanding corona. By jointly fitting the lag-energy spectra in a number of broad frequency ranges with the reverberation model reltrans, we find the increase in reverberation lag is best described by an increase in the X-ray coronal height. This result, along with the finding that the corona contracts in the hard state, suggests a close relationship between spatial extent of the X-ray corona and the radio jet. We find the corona expansion (as probed by reverberation) precedes a radio flare by ~5 days, which may suggest that the hard-to-soft transition is marked by the corona expanding vertically and launching a jet knot that propagates along the jet stream at relativistic velocities.

astro-ph.HE↗

arXiv2021

A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification

Graph convolutional neural network provides good solutions for node classification and other tasks with non-Euclidean data. There are several graph convolutional models that attempt to develop deep networks but do not cause serious over-smoothing at the same time. Considering that the wavelet transform generally has a stronger ability to extract useful information than the Fourier transform, we propose a new deep graph wavelet convolutional network (DeepGWC) for semi-supervised node classification tasks. Based on the optimized static filtering matrix parameters of vanilla graph wavelet neural networks and the combination of Fourier bases and wavelet ones, DeepGWC is constructed together with the reuse of residual connection and identity mappings in network architectures. Extensive experiments on three benchmark datasets including Cora, Citeseer, and Pubmed are conducted. The experimental results demonstrate that our DeepGWC outperforms existing graph deep models with the help of additional wavelet bases and achieves new state-of-the-art performances eventually.

cs.LG↗