Search

Due to the vast testing space, the increasing demand for effective and efficient testing of deep neural networks (DNNs) has led to the development of various DNN test case prioritization techniques. However, the fact that DNNs can deliver high-confidence predictions for incorrectly predicted examples, known as the over-confidence problem, causes these methods to fail to reveal high-confidence errors. To address this limitation, in this work, we propose FAST, a method that boosts existing prioritization methods through guided FeAture SelecTion. FAST is based on the insight that certain features may introduce noise that affects the model's output confidence, thereby contributing to high-confidence errors. It quantifies the importance of each feature for the model's correct predictions, and then dynamically prunes the information from the noisy features during inference to derive a new probability vector for the uncertainty estimation. With the help of FAST, the high-confidence errors and correctly classified examples become more distinguishable, resulting in higher APFD (Average Percentage of Fault Detection) values for test prioritization, and higher generalization ability for model enhancement. We conduct extensive experiments to evaluate FAST across a diverse set of model structures on multiple benchmark datasets to validate the effectiveness, efficiency, and scalability of FAST compared to the state-of-the-art prioritization techniques.

A promising architecture for next-generation, low energy spintronic devices uses skyrmions -- nanoscale whirlpools of magnetic moment -- as information carriers. Notably, schemes for racetrack memory have been proposed in which skyrmions and antiskyrmions, their antiparticle, serve as the logical bits 1 and 0. However, major challenges exist to designing skyrmion-antiskyrmion based computing. The presence of both particles in one material is often mutually exclusive such that few systems have been identified in which they coexist, and in these systems their appearance is stochastic rather than deterministic. Here, we create a tunable skyrmion-antiskyrmion system in FeGe films through ion-irradiation and annealing, and detail the structural properties of the films under these various conditions. Specifically, we irradiate epitaxial B20-phase FeGe films with 2.8 MeV Au$^{4+}$ ions, showing evidence that the amorphized regions preferentially host antiskyrmions at densities controlled by the irradiation fluence. In this work, we focus on a subsequent, systematic electron diffraction study with in-situ annealing, demonstrating the ability to recrystallize controllable fractions of the material at temperatures ranging from approximately 150$^{\circ}$ C to 250$^{\circ}$ C, enabling further tunability of skyrmion/antiskyrmion populations. We describe the crystallization kinetics using the Johnson-Mehl-Avrami-Kolmogorov model, finding that growth of crystalline grains is consistent with diffusion-controlled one-to-two dimensional growth with a decreasing nucleation rate. The procedures developed here can be applied towards creation of skyrmion-antiskyrmion systems for energy-efficient, high-density data storage, spin wave emission produced by skyrmion-antiskyrmion pair annihilation, and more generally testbeds for research on skyrmion-antiskyrmion liquids and crystals.

Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neural network predictions to bounded perturbations of an input. However, verifying properties concerning the preimage, i.e., the set of inputs satisfying an output property, requires abstractions in the input space. We present a general framework for preimage abstraction that produces under- and over-approximations of any polyhedral output set. Our framework employs cheap parameterised linear relaxations of the neural network, together with an anytime refinement procedure that iteratively partitions the input region by splitting on input features and neurons. The effectiveness of our approach relies on carefully designed heuristics and optimization objectives to achieve rapid improvements in the approximation volume. We evaluate our method on a range of tasks, demonstrating significant improvement in efficiency and scalability to high-input-dimensional image classification tasks compared to state-of-the-art techniques. Further, we showcase the application to quantitative verification and robustness analysis, presenting a sound and complete algorithm for the former and providing sound quantitative results for the latter., Comment: arXiv admin note: text overlap with arXiv:2305.03686

Model reuse techniques can reduce the resource requirements for training high-performance deep neural networks (DNNs) by leveraging existing models. However, unauthorized reuse and replication of DNNs can lead to copyright infringement and economic loss to the model owner. This underscores the need to analyze the reuse relation between DNNs and develop copyright protection techniques to safeguard intellectual property rights. Existing white-box testing-based approaches cannot address the common heterogeneous reuse case where the model architecture is changed, and DNN fingerprinting approaches heavily rely on generating adversarial examples with good transferability, which is known to be challenging in the black-box setting. To bridge the gap, we propose NFARD, a Neuron Functionality Analysis-based Reuse Detector, which only requires normal test samples to detect reuse relations by measuring the models' differences on a newly proposed model characterization, i.e., neuron functionality (NF). A set of NF-based distance metrics is designed to make NFARD applicable to both white-box and black-box settings. Moreover, we devise a linear transformation method to handle heterogeneous reuse cases by constructing the optimal projection matrix for dimension consistency, significantly extending the application scope of NFARD. To the best of our knowledge, this is the first adversarial example-free method that exploits neuron functionality for DNN copyright protection. As a side contribution, we constructed a reuse detection benchmark named Reuse Zoo that covers various practical reuse techniques and popular datasets. Extensive evaluations on this comprehensive benchmark show that NFARD achieves F1 scores of 0.984 and 1.0 for detecting reuse relationships in black-box and white-box settings, respectively, while generating test suites 2 ~ 99 times faster than previous methods., Comment: 12 pages, 5 figures

The ubiquity of deep learning algorithms in various applications has amplified the need for assuring their robustness against small input perturbations such as those occurring in adversarial attacks. Existing complete verification techniques offer provable guarantees for all robustness queries but struggle to scale beyond small neural networks. To overcome this computational intractability, incomplete verification methods often rely on convex relaxation to over-approximate the nonlinearities in neural networks. Progress in tighter approximations has been achieved for piecewise linear functions. However, robustness verification of neural networks for general activation functions (e.g., Sigmoid, Tanh) remains under-explored and poses new challenges. Typically, these networks are verified using convex relaxation techniques, which involve computing linear upper and lower bounds of the nonlinear activation functions. In this work, we propose a novel parameter search method to improve the quality of these linear approximations. Specifically, we show that using a simple search method, carefully adapted to the given verification problem through state-of-the-art algorithm configuration techniques, improves the average global lower bound by 25% on average over the current state of the art on several commonly used local robustness verification benchmarks.

Skyrmions and antiskyrmions are nanoscale swirling textures of magnetic moments formed by chiral interactions between atomic spins in magnetic non-centrosymmetric materials and multilayer films with broken inversion symmetry. These quasiparticles are of interest for use as information carriers in next-generation, low-energy spintronic applications. To develop skyrmion-based memory and logic, we must understand skyrmion-defect interactions with two main goals -- determining how skyrmions navigate intrinsic material defects and determining how to engineer disorder for optimal device operation. Here, we introduce a tunable means of creating a skyrmion-antiskyrmion system by engineering the disorder landscape in FeGe using ion irradiation. Specifically, we irradiate epitaxial B20-phase FeGe films with 2.8 MeV Au$^{4+}$ ions at varying fluences, inducing amorphous regions within the crystalline matrix. Using low-temperature electrical transport and magnetization measurements, we observe a strong topological Hall effect with a double-peak feature that serves as a signature of skyrmions and antiskyrmions. These results are a step towards the development of information storage devices that use skyrmions and anitskyrmions as storage bits and our system may serve as a testbed for theoretically predicted phenomena in skyrmion-antiskyrmion crystals.

Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for deployment in a wide range of applications, such as autonomous systems, medical diagnosis and natural language processing. Early adoption of AI technology for real-world applications has not been without problems, particularly for neural networks, which may be unstable and susceptible to adversarial examples. In the longer term, appropriate safety assurance techniques need to be developed to reduce potential harm due to avoidable system failures and ensure trustworthiness. Focusing on certification and explainability, this paper provides an overview of techniques that have been developed to ensure safety of AI decisions and discusses future challenges.

Heterostructures of two-dimensional (2D) van der Waals (vdW) magnets and topological insulators (TI) are of substantial interest as candidate materials for efficient spin-torque switching, quantum anomalous Hall effect, and chiral spin textures. However, since many of the vdW magnets have Curie temperatures below room temperature, we want to understand how materials can be modified to stabilize their magnetic ordering to higher temperatures. In this work, we utilize molecular beam epitaxy to systematically tune the Curie temperature ($T_C$) in thin film Fe$_3$GeTe$_2$/Bi$_2$Te$_3$ from bulk-like values ($\sim$220 K) to above room temperature by increasing the growth temperature from 300 $^\circ$C to 375 $^\circ$C. For samples grown at 375 $^\circ$C, cross-sectional scanning transmission electron microscopy (STEM) reveals the spontaneous formation of different Fe$_m$Ge$_n$Te$_2$ compositions (e.g. Fe$_5$Ge$_2$Te$_2$ and Fe$_7$Ge$_6$Te$_2$) as well as intercalation in the vdW gaps, which are possible origins of the enhanced Curie temperature. This observation paves the way for developing various Fe$_m$Ge$_n$Te$_2$/TI heterostructures with novel properties., Comment: 8 pages, 4 figures

Recurrent Neural Networks (RNNs) have achieved tremendous success in processing sequential data, yet understanding and analyzing their behaviours remains a significant challenge. To this end, many efforts have been made to extract finite automata from RNNs, which are more amenable for analysis and explanation. However, existing approaches like exact learning and compositional approaches for model extraction have limitations in either scalability or precision. In this paper, we propose a novel framework of Weighted Finite Automata (WFA) extraction and explanation to tackle the limitations for natural language tasks. First, to address the transition sparsity and context loss problems we identified in WFA extraction for natural language tasks, we propose an empirical method to complement missing rules in the transition diagram, and adjust transition matrices to enhance the context-awareness of the WFA. We also propose two data augmentation tactics to track more dynamic behaviours of RNN, which further allows us to improve the extraction precision. Based on the extracted model, we propose an explanation method for RNNs including a word embedding method -- Transition Matrix Embeddings (TME) and TME-based task oriented explanation for the target RNN. Our evaluation demonstrates the advantage of our method in extraction precision than existing approaches, and the effectiveness of TME-based explanation method in applications to pretraining and adversarial example generation.

Magnetic van der Waals heterostructures provide a unique platform to study magnetism and spintronics device concepts in the two-dimensional limit. Here, we report studies of exchange bias from the van der Waals antiferromagnet CrSBr acting on the van der Waals ferromagnet Fe3GeTe2 (FGT). The orientation of the exchange bias is along the in-plane easy axis of CrSBr, perpendicular to the out-of-plane anisotropy of the FGT, inducing a strongly tilted magnetic configuration in the FGT. Furthermore, the in-plane exchange bias provides sufficient symmetry breaking to allow deterministic spin-orbit torque switching of the FGT in CrSBr/FGT/Pt samples at zero applied magnetic field. A minimum thickness of the CrSBr greater than 10 nm is needed to provide a non-zero exchange bias at 30 K.

Neural network verification mainly focuses on local robustness properties, which can be checked by bounding the image (set of outputs) of a given input set. However, often it is important to know whether a given property holds globally for the input domain, and if not then for what proportion of the input the property is true. To analyze such properties requires computing preimage abstractions of neural networks. In this work, we propose an efficient anytime algorithm for generating symbolic under-approximations of the preimage of any polyhedron output set for neural networks. Our algorithm combines a novel technique for cheaply computing polytope preimage under-approximations using linear relaxation, with a carefully-designed refinement procedure that iteratively partitions the input region into subregions using input and ReLU splitting in order to improve the approximation. Empirically, we validate the efficacy of our method across a range of domains, including a high-dimensional MNIST classification task beyond the reach of existing preimage computation methods. Finally, as use cases, we showcase the application to quantitative verification and robustness analysis. We present a sound and complete algorithm for the former, which exploits our disjoint union of polytopes representation to provide formal guarantees. For the latter, we find that our method can provide useful quantitative information even when standard verifiers cannot verify a robustness property.

While Feedforward Neural Networks (FNNs) have achieved remarkable success in various tasks, they are vulnerable to adversarial examples. Several techniques have been developed to verify the adversarial robustness of FNNs, but most of them focus on robustness verification against the local perturbation neighborhood of a single data point. There is still a large research gap in global robustness analysis. The global-robustness verifiable framework DeepGlobal has been proposed to identify \textit{all} possible Adversarial Dangerous Regions (ADRs) of FNNs, not limited to data samples in a test set. In this paper, we propose a complete specification and implementation of DeepGlobal utilizing the SMT solver Z3 for more explicit definition, and propose several improvements to DeepGlobal for more efficient verification. To evaluate the effectiveness of our implementation and improvements, we conduct extensive experiments on a set of benchmark datasets. Visualization of our experiment results shows the validity and effectiveness of the approach., Comment: Accepted By SEKE 2023

We complete measurements of interconversions among the full triad of thermal gradients, charge currents, and spin currents in the topological insulator Bi$_2$Se$_3$ by quantifying the efficiency with which thermal gradients can generate transverse spin currents. We accomplish this by comparing the spin Nernst magneto-thermopower to the spin Hall magnesistance for bilayers of Bi$_2$Se$_3$/CoFeB. We find that Bi$_2$Se$_3$ does generate substantial thermally-driven spin currents. A lower bound for the ratio of spin current to thermal gradient is $J_s/\nabla_x T$ = (4.9 $\pm$ 0.9) $\times$ 10$^{6}$ ($\hbar/2e$) A m$^{-2}$ / K $\mu$m$^{-1}$, and a lower bound for the magnitude of the spin Nernst ratio is $-$0.61 $\pm$ 0.11. The spin Nernst ratio for Bi$_2$Se$_3$ is the largest among all materials measured to date, 2-3 times larger compared to previous measurements for the heavy metals Pt and W.

Recurrent Neural Networks (RNNs) have achieved tremendous success in sequential data processing. However, it is quite challenging to interpret and verify RNNs' behaviors directly. To this end, many efforts have been made to extract finite automata from RNNs. Existing approaches such as exact learning are effective in extracting finite-state models to characterize the state dynamics of RNNs for formal languages, but are limited in the scalability to process natural languages. Compositional approaches that are scablable to natural languages fall short in extraction precision. In this paper, we identify the transition sparsity problem that heavily impacts the extraction precision. To address this problem, we propose a transition rule extraction approach, which is scalable to natural language processing models and effective in improving extraction precision. Specifically, we propose an empirical method to complement the missing rules in the transition diagram. In addition, we further adjust the transition matrices to enhance the context-aware ability of the extracted weighted finite automaton (WFA). Finally, we propose two data augmentation tactics to track more dynamic behaviors of the target RNN. Experiments on two popular natural language datasets show that our method can extract WFA from RNN for natural language processing with better precision than existing approaches. Our code is available at https://github.com/weizeming/Extract_WFA_from_RNN_for_NL., Comment: Accepted by ICFEM 2022

We demonstrate advantages of samples made by mechanical stacking of exfoliated van der Waals materials for controlling the topological surface state of a 3-dimensional topological insulator (TI) via interaction with an adjacent magnet layer. We assemble bilayers with pristine interfaces using exfoliated flakes of the TI BiSbTeSe2 and the magnet Cr2Ge2Te6, thereby avoiding problems caused by interdiffusion that can affect interfaces made by top-down deposition methods. The samples exhibit an anomalous Hall effect (AHE) with abrupt hysteretic switching. For the first time in samples composed of a TI and a separate ferromagnetic layer, we demonstrate that the amplitude of the AHE can be tuned via gate voltage with a strong peak near the Dirac point. This is the signature expected for the AHE due to Berry curvature associated with an exchange gap induced by interaction between the topological surface state and an out-of-plane-oriented magnet., Comment: submitted version

Efficient manipulation of antiferromagnetically coupled materials that are integration-friendly and have strong perpendicular magnetic anisotropy (PMA) is of great interest for low-power, fast, dense magnetic storage and computing. Here, we report a distinct, giant bulk damping-like spin-orbit torque in strong-PMA ferrimagnetic Fe100-xTbx single layers that are integration-friendly (composition-uniform, amorphous, sputter-deposited). For sufficiently-thick layers, this bulk torque is constant in the efficiency per unit layer thickness, {\xi}_DL^j/t, with a record-high value of 0.036nm-1, and the dampinglike torque efficiency {\xi}_DL^j achieves very large values for thick layers, up to 300% for 90 nm layers. This giant bulk torque by itself switches tens of nm thick Fe100-xTbx layers that have very strong PMA and high coercivity at current densities as low as a few MA/cm2. Surprisingly, for a given layer thickness, {\xi}_DL^j shows strong composition dependence and becomes negative for composition where the total angular momentum is oriented parallel to the magnetization rather than antiparallel. Our findings of giant bulk spin torque efficiency and intriguing torque-compensation correlation will stimulate study of such unique spin-orbit phenomena in a variety of ferrimagnetic hosts. This work paves a promising avenue for developing ultralow-power, fast, dense ferrimagnetic storage and computing devices., Comment: To appear in Applied Physics Reviews

Crime prediction is crucial for public safety and resource optimization, yet is very challenging due to two aspects: i) the dynamics of criminal patterns across time and space, crime events are distributed unevenly on both spatial and temporal domains; ii) time-evolving dependencies between different types of crimes (e.g., Theft, Robbery, Assault, Damage) which reveal fine-grained semantics of crimes. To tackle these challenges, we propose Spatial-Temporal Sequential Hypergraph Network (ST-SHN) to collectively encode complex crime spatial-temporal patterns as well as the underlying category-wise crime semantic relationships. In specific, to handle spatial-temporal dynamics under the long-range and global context, we design a graph-structured message passing architecture with the integration of the hypergraph learning paradigm. To capture category-wise crime heterogeneous relations in a dynamic environment, we introduce a multi-channel routing mechanism to learn the time-evolving structural dependency across crime types. We conduct extensive experiments on two real-world datasets, showing that our proposed ST-SHN framework can significantly improve the prediction performance as compared to various state-of-the-art baselines. The source code is available at: https://github.com/akaxlh/ST-SHN., Comment: This paper has been published as a research paper at IJCAI 2021

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global inter-region dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework-Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on several real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines. Source codes of implementations are available at https://github.com/jill001/ST-GDN., Comment: Published as a paper at AAAI 2021

Accurate user and item embedding learning is crucial for modern recommender systems. However, most existing recommendation techniques have thus far focused on modeling users' preferences over singular type of user-item interactions. Many practical recommendation scenarios involve multi-typed user interactive behaviors (e.g., page view, add-to-favorite and purchase), which presents unique challenges that cannot be handled by current recommendation solutions. In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions. To tackle these challenges, this work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT), to investigate multi-typed interactive patterns between users and items in recommender systems. Specifically, KHGT is built upon a graph-structured neural architecture to i) capture type-specific behavior characteristics; ii) explicitly discriminate which types of user-item interactions are more important in assisting the forecasting task on the target behavior. Additionally, we further integrate the graph attention layer with the temporal encoding strategy, to empower the learned embeddings be reflective of both dedicated multiplex user-item and item-item relations, as well as the underlying interaction dynamics. Extensive experiments conducted on three real-world datasets show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings. Our implementation code is available at https://github.com/akaxlh/KHGT.

We report measurements demonstrating that when the Neel vector of the collinear antiferromagnet RuO2 is appropriately canted relative to the sample plane, the antiferromagnet generates a substantial out of plane damping-like torque. The measurements are in good accord with predictions that when an electric field, E is applied to the spin split band structure of RuO2 it can cause a strong transverse spin current even in the absence of spin-orbit coupling. This produces characteristic changes in all three components of the E induced torque vector as a function of the angle of E relative to the crystal axes, corresponding to a spin current with a well defined tilted spin orientation s approximately (but not exactly) parallel to the Neel vector, flowing perpendicular to both E and S. This angular dependence is the signature of an antiferromagnetic spin Hall effect with symmetries that are distinct from other mechanisms of spin-current generation reported in antiferromagnetic or ferromagnetic materials.