Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks. Differentiable neural computer (DNC) is a novel computing machine with DNN as its central controller operating on an external memory module for data processing. The unique architecture of DNC contributes to its state-of-the-art performance in tasks which requires the ability to represent variables and data structure as well as to store data over long timescales. However, there still lacks a comprehensive study on how adversarial examples affect DNC in terms of robustness. In this paper, we propose metamorphic relation based adversarial techniques for a range of tasks described in the natural processing language domain. We show that the near-perfect performance of the DNC in bAbI logical question answering tasks can be degraded by adversarially injected sentences. We further perform in-depth study on the role of DNC's memory size in its robustness and analyze the potential reason causing why DNC fails. Our study demonstrates the current challenges and potential opportunities towards constructing more robust DNCs.
Adversarial attacks are small, carefully crafted perturbations, imperceptible to the naked eye; that when added to an image cause deep learning models to misclassify the image with potentially detrimental outcomes. With the rise of artificial intelligence models in consumer safety and security intensive industries such as self-driving cars, camera surveillance and face recognition, there is a growing need for guarding against adversarial attacks. In this paper, we present an approach that uses metamorphic testing principles to automatically detect such adversarial attacks. The approach can det…
Deep Neural Networks (DNN) applications are increasingly becoming a part of our everyday life, from medical applications to autonomous cars. Traditional validation of DNN relies on accuracy measures, however, the existence of adversarial examples has highlighted the limitations of these accuracy measures, raising concerns especially when DNN are integrated into safety-critical systems. In this paper, we present HOMRS, an approach to boost metamorphic testing by automatically building a small optimized set of high order metamorphic relations from an initial set of elementary metamorphic relatio…
Neural network test cases are meant to exercise different reasoning paths in an architecture and used to validate the prediction outcomes. In this paper, we introduce "computational profiles" as vectors of neuron activation levels. We investigate the distribution of computational profile likelihood of metamorphic test cases with respect to the likelihood distributions of training, test and error control cases. We estimate the non-parametric probability densities of neuron activation levels for each distinct output class. Probabilities are inferred using training cases only, without any additio…
Advanced metamorphic malware and ransomware, by using obfuscation, could alter their internal structure with every attack. If such malware could intrude even into any of the IoT networks, then even if the original malware instance gets detected, by that time it can still infect the entire network. It is challenging to obtain training data for such evasive malware. Therefore, in this paper, we present ADVERSARIALuscator, a novel system that uses specialized Adversarial-DRL to obfuscate malware at the opcode level and create multiple metamorphic instances of the same. To the best of our knowledg…
An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images and other structured model inputs, but not for categorical sequences models. Successful attacks on classifiers of categorical sequences are challenging because the model input is tokens from finite sets, so a classifier score is non-differentiable with respect to inputs, and gradient-based attacks are not applicable. Common approaches deal with this problem w…
We designed and developed DOOM (Adversarial-DRL based Opcode level Obfuscator to generate Metamorphic malware), a novel system that uses adversarial deep reinforcement learning to obfuscate malware at the op-code level for the enhancement of IDS. The ultimate goal of DOOM is not to give a potent weapon in the hands of cyber-attackers, but to create defensive-mechanisms against advanced zero-day attacks. Experimental results indicate that the obfuscated malware created by DOOM could effectively mimic multiple-simultaneous zero-day attacks. To the best of our knowledge, DOOM is the first system …
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Huawei Noah’s Ark lab（华为诺亚方舟实验室）；HSE University（高等经济大学）；Oxford University（牛津大学）
Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial attack scenario: check if a small perturbation of an input can fool a model. Due to the discrete nature of textual data, gradient-based adversarial methods, widely used in computer vision, are not applicable per~se. The standard strategy to overcome this issue is to develop token-level transformations, which do not take the whole sentence into account. In th…
Neural network (NN) interatomic potentials provide fast prediction of potential energy surfaces, closely matching the accuracy of the electronic structure methods used to produce the training data. However, NN predictions are only reliable within well-learned training domains, and show volatile behavior when extrapolating. Uncertainty quantification approaches can flag atomic configurations for which prediction confidence is low, but arriving at such uncertain regions requires expensive sampling of the NN phase space, often using atomistic simulations. Here, we exploit automatic differentiatio…
Adversarial training is one of the most effective defenses against adversarial attacks. Previous works suggest that overfitting is a dominant phenomenon in adversarial training leading to a large generalization gap between test and train accuracy in neural networks. In this work, we show that the observed generalization gap is closely related to the choice of the activation function. In particular, we show that using activation functions with low (exact or approximate) curvature values has a regularization effect that significantly reduces both the standard and robust generalization gaps in ad…
University of Toronto（多伦多大学）；Carnegie Mellon University（卡内基梅隆大学）；McGill University（麦吉尔大学）
Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according to a measurement norm. This evaluation, however, has limited practical utility since perturbations in the pixel space do not correspond to underlying real-world phenomena of image formation that lead to them and has no security motivation attached. Pixels in natural images are mea…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；NVIDIA（英伟达）；California Institute of Technology（加州理工学院）；Stanford University（斯坦福大学）
Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge this gap, we propose to study the adversarial robustness of data-driven trajectory prediction systems. We devise an optimization-based adversarial attack framework that leverages a carefully-designed differentiable dynamic model to generate realistic adversarial trajectories. Empirically, we benchmark the adversarial robustness of state-of-the-art prediction…
Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with adversarially optimized snow. At the core of our attack is a differentiable renderer that consistently integrates photorealistic snowflakes with realistic motion into the 3D scene. Through optimization we obtain adversarial snow that significantly impacts the optical flow while being indistinguishable from ordinary snow. Surprisingly, the impact of our novel attack…
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）
Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods that offer minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse for linear and for differentiable classifiers. Finally, we show that reg…
Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly trained. In this paper, we propose a differentiable duration method for learning monotonic alignments between input and output sequences. Our method is based on a soft-duration mechanism that optimizes a stochastic process in expectation. Using this differentiable duration method, we introduce AutoTTS, a direct text-to-waveform speech synthesis model. AutoTTS en…
Recent works show that deep neural networks trained on image classification dataset bias towards textures. Those models are easily fooled by applying small high-frequency perturbations to clean images. In this paper, we learn robust image classification models by removing high-frequency components. Specifically, we develop a differentiable high-frequency suppression module based on discrete Fourier transform (DFT). Combining with adversarial training, we won the 5th place in the IJCAI-2019 Alibaba Adversarial AI Challenge. Our code is available online.
JD Technology（京东科技）；University of California, Los Angeles（加州大学洛杉矶分校）
We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. Plenty of previous works investigated what kind of attacks to the surrogate model can generate more transferable adversarial examples, but their performances are still limited due to the mismatches between surrogate models and the target model. In this paper, we tackle this problem from a novel angle -- instead of using the original surrogate models, can we obtain a Meta-Surrogat…
While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and adversarial training have been proposed, but often followed by new, stronger attacks that defeat these defenses. Can we somehow end this arms race? In this work, we study this problem for neural networks with one hidden layer. We first propose a method based on a semidefinite relaxation that outputs a certificate that for a given network and test input, no attack…
Differentiable architecture search (DARTS) is a prevailing NAS solution to identify architectures. Based on the continuous relaxation of the architecture space, DARTS learns a differentiable architecture weight and largely reduces the search cost. However, its stability has been challenged for yielding deteriorating architectures as the search proceeds. We find that the precipitous validation loss landscape, which leads to a dramatic performance drop when distilling the final architecture, is an essential factor that causes instability. Based on this observation, we propose a perturbation-base…
A robustness certificate is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For {\it any} input perturbations with a magnitude smaller than the certificate value, the classification output will provably remain unchanged. Exactly computing the robustness certificates for neural networks is difficult since it requires solving a non-convex optimization. In this paper, we provide computationally-efficient robustness certificates for neural networks with differentiable activation functions in two steps. First, we show that if the eigenvalues of…
Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations. Existing attack methods for k-nearest neighbor~(kNN) based algorithms either require large perturbations or are not applicable for large k. To handle this problem, this paper proposes a new method called AdvKNN for evaluating the adversarial robustness of kNN-based models. Firstly, we propose a deep kNN block to approximate the output of kNN methods, which is differentiable thus can provide gradients f…
Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly, attacks often craft adversarial examples in such domain. However, "adversarial" examples may become benign after denormalizing them back into the discrete integer domain, known as the discretization problem. This problem was mentioned in some work, but has received relatively little attention. In this work, we first conduct a comprehensive study of existing methods and tools f…
Institute of Mathematical Sciences, ICMAT-CSIC（数学科学研究所（ICMAT-CSIC））
Malware constitutes a major global risk affecting millions of users each year. Standard algorithms in detection systems perform insufficiently when dealing with malware passed through obfuscation tools. We illustrate this studying in detail an open source metamorphic software, making use of a hybrid framework to obtain the relevant features from binaries. We then provide an improved alternative solution based on adversarial risk analysis which we illustrate describe with an example.
Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses for securing SRSs. According to the characteristic of SRSs, we present 22 diverse transformations and thoroughly evaluate them using 7 recent promising adversarial attacks (4 white-box and 3 black-box) on speaker recognition. With careful regard for best practices in defense evaluations, we analyze the strength of transformations to withstand adaptive attacks…
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Generative modeling of 3D brain MRIs presents difficulties in achieving high visual fidelity while ensuring sufficient coverage of the data distribution. In this work, we propose to address this challenge with composable, multiscale morphological transformations in a variational autoencoder (VAE) framework. These transformations are applied to a chosen reference brain image to generate MRI volumes, equipping the model with strong anatomical inductive biases. We structure the VAE latent space in a way such that the model covers the data distribution sufficiently well. We show substantial perfor…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Science and Technology of China（中国科学技术大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-world usage is to append adversarial patches (e.g. logos) to images. Nevertheless, much less have we known about adversarial attacks from 3D rendering views, which is essential for the attack to be persistently strong in the physical world. This paper presents a new 3D adversarial logo attack: we construct an arbitrary shape logo from a 2D texture image and map this image into a 3D adversarial logo via a texture mappi…
Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it can be beneficial. We find that neural networks can learn to use invisible perturbations to encode a rich amount of useful information. In fact, one can exploit this capability for the task of data hiding. We jointly train encoder and decoder networks, where given an input message and cover image, the encoder produces a visually indistinguishable encoded ima…
University of Minnesota（明尼苏达大学）；Queens College, City University of New York（纽约城市大学皇后学院）
Empirical robustness evaluation (RE) of deep learning models against adversarial perturbations entails solving nontrivial constrained optimization problems. Existing numerical algorithms that are commonly used to solve them in practice predominantly rely on projected gradient, and mostly handle perturbations modeled by the $\ell_1$, $\ell_2$ and $\ell_\infty$ distances. In this paper, we introduce a novel algorithmic framework that blends a general-purpose constrained-optimization solver PyGRANSO with Constraint Folding (PWCF), which can add more reliability and generality to the state-of-the-…
Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics
Department of Electrical and Computer Engineering（电气与计算机工程系）；Kummer Institute Center for Artificial Intelligence and Autonomous Systems (KICAIAS)（人工智能与自主系统中心（KICAIAS））；Missouri University of Science and Technology（密苏里科技大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Zhejiang University（浙江大学）；Tencent（腾讯）；Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be leveraged to estimate the robustness of NLP models. Compared with the adversarial example generation in continuous data domain (e.g., image), generating adversarial text that preserves the original meaning is challenging since the text space is discrete and non-differentiable. To handle these challenges, we propose a target-controllable adversarial attack fram…
Recent work on adversarial attack and defense suggests that PGD is a universal $l_\infty$ first-order attack, and PGD adversarial training can significantly improve network robustness against a wide range of first-order $l_\infty$-bounded attacks, represented as the state-of-the-art defense method. However, an obvious weakness of PGD adversarial training is its highly-computational cost in generating adversarial samples, making it computationally infeasible for large and high-resolution real datasets such as the ImageNet dataset. In addition, recent work also has suggested a simple "close-form…
University of Liège（列日大学）；New York University（纽约大学）
Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational Optimization (AVO), a likelihood-free inference algorithm for fitting a non-differentiable generative model incorporating ideas from generative adversarial networks, variational optimization and empirical Bayes. We adapt the training procedure of generative adversarial networks by…
Center for Data Science, Zhejiang University（浙江大学数据科学中心）；Information Hub, The Hong Kong University of Science and Technology（香港科技大学信息枢纽）；College of Computer Science, Zhejiang University（浙江大学计算机科学与技术学院）
Data imputation has been extensively explored to solve the missing data problem. The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications. In this paper, we propose an effective scalable imputation system named SCIS to significantly speed up the training of the differentiable generative adversarial imputation models under accuracy-guarantees for large-scale incomplete data. SCIS consists of two modules, differentiable imputation modeling (DIM) and sample size estimation (SSE). DIM leverages a new masking Sinkhor…
Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
Department of Computer Applications, Cochin University of Science and Technology（计算机应用系，科钦大学科学与技术学院）；Department of Electrical, Computer and Biomedical Engineering, University of Pavia（电气、计算机与生物医学工程系，帕维亚大学）
Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense. Among these methods, adversarial training has been drawing increasing attention because of its simplicity and effectiveness. However, the performance of the adversarial training is greatly limited by the architectures of target DNNs, which often makes the resulting DNNs with poor accuracy and unsatisfactory robustness. To address this problem, we propose DSARA to automatically search for the neural architectures that are accurate and robust after adversarial tr…
A central task of a Disc Jockey (DJ) is to create a mixset of mu-sic with seamless transitions between adjacent tracks. In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. In particular, the generator of the model uses two differentiable digital signal processing components, an equalizer (EQ) and a fader, to mix two tracks selected by a data generation pipeline. The generator has to set the parameters of the EQs and fader in such away that the resulting mix resembles real mixes created b…
There is considerable evidence that deep neural networks are vulnerable to adversarial perturbations applied directly to their digital inputs. However, it remains an open question whether this translates to vulnerabilities in real systems. For example, an attack on self-driving cars would in practice entail modifying the driving environment, which then impacts the video inputs to the car's controller, thereby indirectly leading to incorrect driving decisions. Such attacks require accounting for system dynamics and tracking viewpoint changes. We propose a scalable approach for finding adversari…
Zhejiang University（浙江大学）；JD Explore Academy（京东探索研究院）；Tencent AI Lab（腾讯人工智能实验室）；Tencent Data Platform（腾讯数据平台部）；Microsoft（微软）
Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. The intrinsic problem complexity poses the challenge to enhance the performance of generative networks. In this work, we aim to boost model learning from the perspective of network architectures, by incorporating recent progress on automated architecture search into GANs. To this end, we propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN. The sear…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
We propose a method that enables practitioners to conveniently incorporate custom non-decomposable performance metrics into differentiable learning pipelines, notably those based upon neural network architectures. Our approach is based on the recently developed adversarial prediction framework, a distributionally robust approach that optimizes a metric in the worst case given the statistical summary of the empirical distribution. We formulate a marginal distribution technique to reduce the complexity of optimizing the adversarial prediction formulation over a vast range of non-decomposable met…
The current state-of-the-art Android malware detection systems are based on machine learning and deep learning models. Despite having superior performance, these models are susceptible to adversarial attacks. Therefore in this paper, we developed eight Android malware detection models based on machine learning and deep neural network and investigated their robustness against adversarial attacks. For this purpose, we created new variants of malware using Reinforcement Learning, which will be misclassified as benign by the existing Android malware detection models. We propose two novel attack st…
In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched architectures are prone to adversarial attacks. A small perturbation of the input data can render the architecture to change prediction outcomes significantly. To address this problem, we propose methods to perform differentiable search of robust neural architectures. In our methods, two differentiable metrics are defined to measure architectures' robustness, ba…
Technion - Israel Institute of Technology（以色列理工学院）
Generative adversarial learning is a popular new approach to training generative models which has been proven successful for other related problems as well. The general idea is to maintain an oracle $D$ that discriminates between the expert's data distribution and that of the generative model $G$. The generative model is trained to capture the expert's distribution by maximizing the probability of $D$ misclassifying the data it generates. Overall, the system is \emph{differentiable} end-to-end and is trained using basic backpropagation. This type of learning was successfully applied to the pro…
National Innovation Institute of Defense Technology（国防科技创新研究院）
Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve the accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art …
This paper proposes an encoder-decoder architecture grounded on Generative Adversarial Networks (GANs), that generates a sequence of activities and their timestamps in an end-to-end way. GANs work well with differentiable data such as images. However, a suffix is a sequence of categorical items. To this end, we use the Gumbel-Softmax distribution to get a differentiable continuous approximation. The training works by putting one neural network against the other in a two-player game (hence the "adversarial" nature), which leads to generating suffixes close to the ground truth. From the experime…
