arXiv subjects

Jie Yin

Publications and source records attributed to Jie Yin.

At least 55 records · Page 3Linked to original sources

arXiv2022

DeepC2: AI-powered Covert Command and Control on OSNs

Command and control (C&C) is important in an attack. It transfers commands from the attacker to the malware in the compromised hosts. Currently, some attackers use online social networks (OSNs) in C&C tasks. There are two main problems in the C&C on OSNs. First, the process for the malware to find the attacker is reversible. If the malware sample is analyzed by the defender, the attacker would be exposed before publishing the commands. Second, the commands in plain or encrypted form are regarded as abnormal contents by OSNs, which would raise anomalies and trigger restrictions on the attacker. The defender can limit the attacker once it is exposed. In this work, we propose DeepC2, an AI-powered C&C on OSNs, to solve these problems. For the reversible hard-coding, the malware finds the attacker using a neural network model. The attacker's avatars are converted into a batch of feature vectors, and the defender cannot recover the avatars in advance using the model and the feature vectors. To solve the abnormal contents on OSNs, hash collision and text data augmentation are used to embed commands into normal contents. The experiment on Twitter shows that command-embedded tweets can be generated efficiently. The malware can find the attacker covertly on OSNs. Security analysis shows it is hard to recover the attacker's identifiers in advance.

cs.CR↗

arXiv2022

EvilModel 2.0: Bringing Neural Network Models into Malware Attacks

Security issues have gradually emerged with the continuous development of artificial intelligence (AI). Earlier work verified the possibility of converting neural network models into stegomalware, embedding malware into a model with limited impact on the model's performance. However, existing methods are not applicable in real-world attack scenarios and do not attract enough attention from the security community due to performance degradation and additional workload. Therefore, we propose an improved stegomalware EvilModel. By analyzing the composition of the neural network model, three new methods for embedding malware into the model are proposed: MSB reservation, fast substitution, and half substitution, which can embed malware that accounts for half of the model's volume without affecting the model's performance. We built 550 EvilModels using ten mainstream neural network models and 19 malware samples. The experiment shows that EvilModel achieved an embedding rate of 48.52\%. A quantitative algorithm is proposed to evaluate the existing embedding methods. We also design a trigger and propose a threat scenario for the targeted attack. The practicality and effectiveness of the proposed methods were demonstrated by experiments and analyses of the embedding capacity, performance impact, and detection evasion.

cs.CR↗

arXiv2022

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from the over-smoothing problem, where node representations tend to be indistinguishable as more layers are stacked up. The theoretical research to date on deep GCNs has focused primarily on expressive power rather than trainability, an optimization perspective. Compared to expressivity, trainability attempts to address a more fundamental question: Given a sufficiently expressive space of models, can we successfully find a good solution via gradient descent-based optimizers? This work fills this gap by exploiting the Graph Neural Tangent Kernel (GNTK), which governs the optimization trajectory under gradient descent for wide GCNs. We formulate the asymptotic behaviors of GNTK in the large depth, which enables us to reveal the dropping trainability of wide and deep GCNs at an exponential rate in the optimization process. Additionally, we extend our theoretical framework to analyze residual connection-based techniques, which are found to be merely able to mitigate the exponential decay of trainability mildly. Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally. Experimental evaluation consistently confirms using our proposed method can achieve better results compared to relevant counterparts with both infinite-width and finite-width.

cs.LG↗

arXiv2022

Snapping for high-speed and high-efficient, butterfly swimming-like soft flapping-wing robot

Natural selection has tuned many flying and swimming animals across different species to share the same narrow design space for optimal high-efficient and energy-saving locomotion, e.g., their dimensionless Strouhal numbers St that relate flapping frequency and amplitude and forward speed fall within the range of 0.2 < St < 0.4 for peak propulsive efficiency. It is rather challenging to achieve both fast and high-efficient soft-bodied swimming robots with high performances that are comparable to marine animals, due to the observed narrow optimal design space in nature and the compliance of soft body. Here, bioinspired by the wing or fin flapping motion in flying and swimming animals, we report leveraging the generic principle of snapping instabilities in the bistable and multistable flexible pre-curved wings for high-performance, butterfly swimming-like, soft-bodied flapping-wing robots. The soft swimming robot is lightweight (2.8 grams) and demonstrates a record-high speed of 3.74 body length/s (4.8 times faster than the reported fastest soft swimmer), high-efficient (0.2 < St = 0.25 < 0.4), low energy consumption cost, and high maneuverability (a high turning speed of 157o /s). Its high performances largely outperform the state-of-the-art soft swimming robots and are even comparable to its biological counterparts.

physics.app-ph↗

arXiv2022

Informative Pseudo-Labeling for Graph Neural Networks with Few Labels

Graph Neural Networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs. Nevertheless, the challenge of how to effectively learn GNNs with very few labels is still under-explored. As one of the prevalent semi-supervised methods, pseudo-labeling has been proposed to explicitly address the label scarcity problem. It aims to augment the training set with pseudo-labeled unlabeled nodes with high confidence so as to re-train a supervised model in a self-training cycle. However, the existing pseudo-labeling approaches often suffer from two major drawbacks. First, they tend to conservatively expand the label set by selecting only high-confidence unlabeled nodes without assessing their informativeness. Unfortunately, those high-confidence nodes often convey overlapping information with given labels, leading to minor improvements for model re-training. Second, these methods incorporate pseudo-labels to the same loss function with genuine labels, ignoring their distinct contributions to the classification task. In this paper, we propose a novel informative pseudo-labeling framework, called InfoGNN, to facilitate learning of GNNs with extremely few labels. Our key idea is to pseudo label the most informative nodes that can maximally represent the local neighborhoods via mutual information maximization. To mitigate the potential label noise and class-imbalance problem arising from pseudo labeling, we also carefully devise a generalized cross entropy loss with a class-balanced regularization to incorporate generated pseudo labels into model re-training. Extensive experiments on six real-world graph datasets demonstrate that our proposed approach significantly outperforms state-of-the-art baselines and strong self-supervised methods on graphs.

cs.LG↗

arXiv2021

M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots

We introduce M2DGR: a novel large-scale dataset collected by a ground robot with a full sensor-suite including six fish-eye and one sky-pointing RGB cameras, an infrared camera, an event camera, a Visual-Inertial Sensor (VI-sensor), an inertial measurement unit (IMU), a LiDAR, a consumer-grade Global Navigation Satellite System (GNSS) receiver and a GNSS-IMU navigation system with real-time kinematic (RTK) signals. All those sensors were well-calibrated and synchronized, and their data were recorded simultaneously. The ground truth trajectories were obtained by the motion capture device, a laser 3D tracker, and an RTK receiver. The dataset comprises 36 sequences (about 1TB) captured in diverse scenarios including both indoor and outdoor environments. We evaluate state-of-the-art SLAM algorithms on M2DGR. Results show that existing solutions perform poorly in some scenarios. For the benefit of the research community, we make the dataset and tools public. The webpage of our project is https://github.com/SJTU-ViSYS/M2DGR.

cs.RO↗

arXiv2021

A long-lasting guided bone regeneration membrane from sequentially functionalised photoactive atelocollagen

The fast degradation of collagen-based membranes in the biological environment remains a critical challenge, resulting in underperforming Guided Bone Regeneration (GBR) therapy leading to compromised clinical results. Photoactive atelocollagen (AC) systems functionalised with ethylenically unsaturated monomers, such as 4-vinylbenzyl chloride (4VBC), have been shown to generate mechanically competent materials for wound healing, inflammation control and drug delivery, whereby control of the molecular architecture of the AC network is key. Building on this platform, the sequential functionalisation with 4VBC and methacrylic anhydride (MA) was hypothesised to generate UV-cured AC hydrogels with reduced swelling ratio, increased proteolytic stability and barrier functionality for GBR therapy. The sequentially functionalised atelocollagen precursor (SAP) was characterised via TNBS and ninhydrin colourimetric assays, circular dichroism and UV-curing rheometry, which confirmed nearly complete consumption of collagen primary amino groups, preserved triple helices and fast (within 180 s) gelation kinetics, respectively. Hydrogel swelling ratio and compression modulus were adjusted depending on the aqueous environment used for UV-curing, whilst the sequential functionalisation of AC successfully generated hydrogels with superior proteolytic stability in vitro compared to both 4VBC functionalised control and the commercial dental membrane Bio-Gide. These in vitro results were confirmed in vivo via both subcutaneous implantation and a proof-of-concept study in a GBR calvarial model, indicating integrity of the hydrogel and barrier defect, as well as tissue formation following 1-month implantation in rats.

q-bio.TO↗

arXiv2021

Edge but not Least: Cross-View Graph Pooling

Graph neural networks have emerged as a powerful model for graph representation learning to undertake graph-level prediction tasks. Various graph pooling methods have been developed to coarsen an input graph into a succinct graph-level representation through aggregating node embeddings obtained via graph convolution. However, most graph pooling methods are heavily node-centric and are unable to fully leverage the crucial information contained in global graph structure. This paper presents a cross-view graph pooling (Co-Pooling) method to better exploit crucial graph structure information. The proposed Co-Pooling fuses pooled representations learnt from both node view and edge view. Through cross-view interaction, edge-view pooling and node-view pooling seamlessly reinforce each other to learn more informative graph-level representations. Co-Pooling has the advantage of handling various graphs with different types of node attributes. Extensive experiments on a total of 15 graph benchmark datasets validate the effectiveness of our proposed method, demonstrating its superior performance over state-of-the-art pooling methods on both graph classification and graph regression tasks.

cs.LG↗

arXiv2021

Architected kirigami metamorphosis

Kirigami, art of paper cutting, enables two-dimensional sheets transforming into unique shapes which are also hard to reshape once with prescribed cutting patterns. Rare kirigami designs manipulate cuts on three-dimensional objects to compose periodic structures with programmability and/or re-programmability. Here, we propose a new class of three-dimensional modular kirigami by introducing cuts on cuboid-shaped objects, based on which constructing two quasi-three-15 dimensional architected kirigamis with even-flat structural form. We demonstrate the proposed architected kirigamis are with rich mobilities triggered by kinematic bifurcations inherited from their composed modular kirigami, and can undergo living-matter-like metamorphosis evolving into miscellaneous transformable three-dimensional architectures and even a pluripotent platform capable of being re-programmed into curvature different surfaces through inverse design. Such 20 metamorphic structures could find broad applications in reconfigurable metamaterials, transformable robots and architectures.

cond-mat.mtrl-sci↗

arXiv2021

Three-dimensional transformable modular kirigami based programmable architected materials

Metamaterials achieve unprecedented properties from designed architected structures. However, they are often constructed from a single repeating building block that exhibits monotonic shape changes with single degree of freedom, thereby leading to specific spatial forms and limited reconfigurability. Here we introduce a transformable three-dimensional modular kirigami with multiple degrees of freedom that could reconfigure into versatile distinct daughter building blocks. Consequently, the combinatorial and spatial modular assembly of these building blocks could create a wealth of reconfigurable architected materials with diverse structures and unique properties, including reconfigurable 1D periodic column-like materials with bifurcated states, 2D lattice-like architected materials with phase transition of chirality, as well as 3D quasiperiodic yet frustration-free multilayered architected materials in a long-range order with programmable deformation modes. Our strategy opens an avenue to design a new class of modular reconfigurable metamaterials that are reprogrammable and reusable for potential multifunctionality in architectural, phononic, mechanical, and robotic applications.

cond-mat.mtrl-sci↗

arXiv2021

Boundary curvature guided shape-programming kirigami sheets

Kirigami, an ancient paper cutting art, offers a promising strategy for 2D-to-3D shape morphing through cut-guided deformation. Existing kirigami designs for target 3D curved shapes rely on intricate cut patterns in thin sheets, making the inverse design challenging. Motivated by the Gauss-Bonnet theorem that correlates the geodesic curvature along the boundary with the topological Gaussian curvature, here, we exploit programming the curvature of cut boundaries rather than complex cut patterns in kirigami sheets for target 3D curved topologies through both forward and inverse designs. Such a new strategy largely simplifies the inverse design. We demonstrate the achievement of varieties of dynamic 3D shape shifting under both mechanical stretching and remote magnetic actuation, and its potential application as an untethered predator-like kirigami soft robot. This study opens a new avenue to encode boundary curvatures for shape-programing materials with potential applications in shape-morphing structures, soft robots, and multifunctional devices.

physics.app-ph↗

arXiv2021

Human-Understandable Decision Making for Visual Recognition

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that humans cannot fully trust the predictions made by these models. To date, little work has been done on how to align the behaviors of deep learning models with human perception in order to train a human-understandable model. To fill this gap, we propose a new framework to train a deep neural network by incorporating the prior of human perception into the model learning process. Our proposed model mimics the process of perceiving conceptual parts from images and assessing their relative contributions towards the final recognition. The effectiveness of our proposed model is evaluated on two classical visual recognition tasks. The experimental results and analysis confirm our model is able to provide interpretable explanations for its predictions, but also maintain competitive recognition accuracy.

cs.AI↗

arXiv2020

SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional non-related data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on graphs attempt to reuse the classic AL query strategies designed for non-related data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labelled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way. Our framework learns two adversarial components: a graph embedding network that encodes both the unlabelled and labelled nodes into a latent space, expecting to trick the discriminator to regard all nodes as already labelled, and a semi-supervised discriminator network that distinguishes the unlabelled from the existing labelled nodes in the latent space. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labelled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other towards enhancing the active learning performance. Extensive experiments on four real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines.

cs.LG↗

arXiv2020

Leveraging Elastic instabilities for Amplified Performance: spine-inspired high-speed and high-force soft robots

Soft machines typically exhibit slow locomotion speed and low manipulation strength because of intrinsic limitations of soft materials. Here, we present a generic design principle that harnesses mechanical instability for a variety of spine-inspired fast and strong soft machines. Unlike most current soft robots that are designed as inherently and unimodally stable, our design leverages tunable snap-through bistability to fully explore the ability of soft robots to rapidly store and release energy within tens of milliseconds. We demonstrate this generic design principle with three high-performance soft machines: High-speed cheetah-like galloping crawlers with locomotion speeds of 2.68 body length/s, high-speed underwater swimmers (0.78 body length/s), and tunable low-to-high-force soft grippers with over 1 to 103 stiffness modulation (maximum load capacity is 11.4 kg). Our study establishes a new generic design paradigm of next-generation high-performance soft robots that are applicable for multifunctionality, different actuation methods, and materials at multiscales.

physics.app-ph↗

arXiv2020

Cost-effectiveness Analysis of Antiepidemic Policies and Global Situation Assessment of COVID-19

With a two-layer contact-dispersion model and data in China, we analyze the cost-effectiveness of three types of antiepidemic measures for COVID-19: regular epidemiological control, local social interaction control, and inter-city travel restriction. We find that: 1) intercity travel restriction has minimal or even negative effect compared to the other two at the national level; 2) the time of reaching turning point is independent of the current number of cases, and only related to the enforcement stringency of epidemiological control and social interaction control measures; 3) strong enforcement at the early stage is the only opportunity to maximize both antiepidemic effectiveness and cost-effectiveness; 4) mediocre stringency of social interaction measures is the worst choice. Subsequently, we cluster countries/regions into four groups based on their control measures and provide situation assessment and policy suggestions for each group.

physics.soc-ph↗

arXiv2019

Latent Adversarial Defence with Boundary-guided Generation

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples with a small perturbation to fool the DNN models to predict wrong labels. To improve the robustness of shared DNN models against adversarial attacks, we propose a novel method called Latent Adversarial Defence (LAD). The proposed LAD method improves the robustness of a DNN model through adversarial training on generated adversarial examples. Different from popular attack methods which are carried in the input space and only generate adversarial examples of repeating patterns, LAD generates myriad of adversarial examples through adding perturbations to latent features along the normal of the decision boundary which is constructed by an SVM with an attention mechanism. Once adversarial examples are generated, we adversarially train the model through augmenting the training data with generated adversarial examples. Extensive experiments on the MNIST, SVHN, and CelebA dataset demonstrate the effectiveness of our model in defending against different types of adversarial attacks.

cs.LG↗

arXiv2019

Attributed Network Embedding via Subspace Discovery

Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology structure to learn node representations, recently proposed attributed network embedding algorithms attempt to integrate rich node content information with network topological structure for enhancing the quality of network embedding. In reality, networks often have sparse content, incomplete node attributes, as well as the discrepancy between node attribute feature space and network structure space, which severely deteriorates the performance of existing methods. In this paper, we propose a unified framework for attributed network embedding-attri2vec-that learns node embeddings by discovering a latent node attribute subspace via a network structure guided transformation performed on the original attribute space. The resultant latent subspace can respect network structure in a more consistent way towards learning high-quality node representations. We formulate an optimization problem which is solved by an efficient stochastic gradient descent algorithm, with linear time complexity to the number of nodes. We investigate a series of linear and non-linear transformations performed on node attributes and empirically validate their effectiveness on various types of networks. Another advantage of attri2vec is its ability to solve out-of-sample problems, where embeddings of new coming nodes can be inferred from their node attributes through the learned mapping function. Experiments on various types of networks confirm that attri2vec is superior to state-of-the-art baselines for node classification, node clustering, as well as out-of-sample link prediction tasks. The source code of this paper is available at https://github.com/daokunzhang/attri2vec.

cs.SI↗

arXiv2019

Switchable Adhesion Actuator for Amphibious Climbing Soft Robot

Climbing soft robots are of tremendous interest in both science and engineering due to their potential applications in intelligent surveillance, inspection, maintenance, and detection under environments away from the ground. The challenge lies in the design of a fast, robust, switchable adhesion actuator to easily attach and detach the vertical surfaces. Here, we propose a new design of pneumatic-actuated bioinspired soft adhesion actuator working both on ground and under water. It is composed of extremely soft bilayer structures with an embedded spiral pneumatic channel resting on top of a base layer with a cavity. Rather than the traditional way of directly pumping air out of the cavity for suction in hard polymer-based adhesion actuator, we inflate air into the top spiral channel to deform into a stable 3D domed shape for achieving negative pressure in the cavity. The characterization of the maximum shear adhesion force of the proposed soft adhesion actuator shows strong and rapid reversible adhesion on multiple types of smooth and semi-smooth surfaces. Based on the switchable adhesion actuator, we design and fabricate a novel load-carrying amphibious climbing soft robot (ACSR) by combining with a soft bending actuator. We demonstrate that it can operate on a wide range of foreign horizontal and vertical surfaces including dry, wet, slippery, smooth, and semi-smooth ones on ground and also under water with certain load-carrying capability. We show that the vertical climbing speed can reach about 286 mm/min (1.6 body length/min) while carrying over 200g object (over 5 times the weight of ACSR itself) during climbing on ground and under water. This research could largely push the boundaries of soft robot capabilities and multifunctionality in window cleaning and underwater inspection under harsh environment.

physics.app-ph↗