Adversarial examples contain small perturbations that can remain imperceptible to human observers but alter the behavior of even the best performing deep learning models and yield incorrect outputs. Since their discovery, adversarial examples have drawn significant attention in machine learning: researchers try to reveal the reasons for their existence and improve the robustness of machine learning models to adversarial perturbations. The state-of-the-art defense is the computationally expensive and very time consuming adversarial training via projected gradient descent (PGD). We hypothesize that adversarial attacks exploit the open space risk of classic monotonic activation functions. This paper introduces the tent activation function with bounded open space risk and shows that tents make deep learning models more robust to adversarial attacks. We demonstrate on the MNIST dataset that a classifier with tents yields an average accuracy of 91.8% against six white-box adversarial attacks, which is more than 15 percentage points above the state of the art. On the CIFAR-10 dataset, our approach improves the average accuracy against the six white-box adversarial attacks to 73.5% from 41.8% achieved by adversarial training via PGD.
Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）；New York University（纽约大学）；Nanyang Technological University（南洋理工大学）；Tianjin University（天津大学）；University of South Carolina（南卡罗来纳大学）
Adversarial training (AT) is one of the most effective ways for improving the robustness of deep convolution neural networks (CNNs). Just like common network training, the effectiveness of AT relies on the design of basic network components. In this paper, we conduct an in-depth study on the role of the basic ReLU activation component in AT for robust CNNs. We find that the spatially-shared and input-independent properties of ReLU activation make CNNs less robust to white-box adversarial attacks with either standard or adversarial training. To address this problem, we extend ReLU to a novel Sp…
Enhancing model prediction confidence on target data is an important objective in Unsupervised Domain Adaptation (UDA). In this paper, we explore adversarial training on penultimate activations, i.e., input features of the final linear classification layer. We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features, as used in previous works. Furthermore, with activation normalization commonly used in domain adaptation to reduce domain gap, we derive two variants and …
Deep neural networks are known to be vulnerable to adversarially perturbed inputs. A commonly used defense is adversarial training, whose performance is influenced by model capacity. While previous works have studied the impact of varying model width and depth on robustness, the impact of increasing capacity by using learnable parametric activation functions (PAFs) has not been studied. We study how using learnable PAFs can improve robustness in conjunction with adversarial training. We first ask the question: how should we incorporate parameters into activation functions to improve robustness…
Tsinghua Berkeley Shenzhen Institute, Tsinghua University（清华大学清华伯克利深圳学院）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Key Lab. of Machine Perception (MoE), School of EECS, Peking University（北京大学信息科学技术学院机器感知与智能教育部重点实验室）；School of Information Technology, Deakin University（迪肯大学信息技术学院）；PCL Research Center of Networks and Communications, Peng Cheng Laboratory（鹏城实验室网络通信研究中心）
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two new characteristics of adversarial examples from the channel-wise activation perspective: 1) the activation magnitudes of adversarial examples are higher than that of natural examples; and 2) the channels are activated more uniformly by adversarial examples than natural examples. We find that the state-of-the-art defense adversarial training has addressed the first issue of high…
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…
Xidian University（西安电子科技大学）；The University of Sydney（悉尼大学）
Deep neural networks (DNNs) are vulnerable to adversarial noise. Preprocessing based defenses could largely remove adversarial noise by processing inputs. However, they are typically affected by the error amplification effect, especially in the front of continuously evolving attacks. To solve this problem, in this paper, we propose to remove adversarial noise by implementing a self-supervised adversarial training mechanism in a class activation feature space. To be specific, we first maximize the disruptions to class activation features of natural examples to craft adversarial examples. Then, …
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered attention map. Accordingly, an attention-based adversarial defense framework is designed to simultaneously rectify the attention map for prediction and preserve the attention area between adversarial and original images. The problem of adding iterat…
University of Central Florida（中佛罗里达大学）；JD AI Research（京东AI研究院）；Tencent AI Lab（腾讯AI实验室）
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNNs have been proposed. In a separate and yet related area, recent works have explored to quantize neural network weights and activation functions into low bit-width to compress model size and reduce computational complexity. In this work, we find that these two different tracks, namely the pursuit of network compactness and robustness, can be merged into one and give rise to networks of both advantages. To the best of…
Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be enco…
State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about the security and generalization of DNNs in real-world conditions, whereas the latter impedes users' trust in their output. In this research, we (1) examine the effect of adversarial robustness on interpretability and (2) present a novel approach for improving the interpretability of DNNs that is based o…
Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术研究院（KAIST））
Deep neural networks are susceptible to adversarial attacks due to the accumulation of perturbations in the feature level, and numerous works have boosted model robustness by deactivating the non-robust feature activations that cause model mispredictions. However, we claim that these malicious activations still contain discriminative cues and that with recalibration, they can capture additional useful information for correct model predictions. To this end, we propose a novel, easy-to-plugin approach named Feature Separation and Recalibration (FSR) that recalibrates the malicious, non-robust ac…
Dalhousie University（达尔豪斯大学）；Universidade de São Paulo（圣保罗大学）
As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can have disastrous consequences. Recent work has shown that commonly used methods for model training often result in fragile abstract representations that are particularly vulnerable to such attacks. This paper presents a visual framework to investigate neural network models subjected to adversarial examples, revealing how models' perception of the adversarial…
Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model. The state of the arts [Baiet al., 2021] and [Yanet al., 2021] explores this feature at the channel level, i.e. the activation of a channel is uniformly scaled by a factor. In this paper, we investigate the intermediate activation manipulation at a more fine-grained level. Instead of uniformly scaling the activation, we individually adjust each element within an activation and thus propose Element-Wise Activation Scaling, dubbed EWAS, to improve CNNs…
Northeastern University（东北大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, interpretability of these perturbations is less explored in the literature. This work aims to better understand the roles of adversarial perturbations and provide visual explanations from pixel, image and network perspectives. We show that adversaries have a promotion-suppression effect (PSE) on neurons' activations and can be primarily categorized into three types: i) suppression-dominated perturbations that mainly r…
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
University of Technology Sydney, Sydney, Australia（技术悉尼大学）；School of Cyber Science and Engineering, Southeast University, Nanjing, China（东南大学计算机科学与工程学院）；Xi'an Jiaotong University, Xi'an, China（西安交通大学）
Isik University（伊希克大学）；University of Stavanger（斯塔万格大学）
In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability scores of each class. In this type of architectures, the loss value of the classifier against any output class is directly proportional to the difference between the final probability score and the label value of the associated class. Standard White-box adversarial evasion attacks, whether targeted or untargeted, mainly try to exploit the gradient of the model loss function to c…
In the recent quest for trustworthy neural networks, we present Spiking Neural Network (SNN) as a potential candidate for inherent robustness against adversarial attacks. In this work, we demonstrate that adversarial accuracy of SNNs under gradient-based attacks is higher than their non-spiking counterparts for CIFAR datasets on deep VGG and ResNet architectures, particularly in blackbox attack scenario. We attribute this robustness to two fundamental characteristics of SNNs and analyze their effects. First, we exhibit that input discretization introduced by the Poisson encoder improves advers…
Recent works have shown that the input domain of any machine learning classifier is bound to contain adversarial examples. Thus we can no longer hope to immune classifiers against adversarial examples and instead can only aim to achieve the following two defense goals: 1) making adversarial examples harder to find, or 2) weakening their adversarial nature by pushing them further away from correctly classified data points. Most if not all the previously suggested defense mechanisms attend to just one of those two goals, and as such, could be bypassed by adaptive attacks that take the defense me…
A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods
Alma Mater Studiorum Università di Bologna（博洛尼亚大学）；Advanced Research Center on Electronic Systems “Ercole De Castro” (ARCES) - Alma Mater Studiorum Università di Bologna（博洛尼亚大学“埃尔科莱·德·卡斯特罗”电子系统高级研究中心）
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified activations to reconstruct the original sample. A human might (and possibly should) notice differences between the original and the adversarial sample. Depending on the attacker-provided constraints, an adversarial sample can exhibit subtle differences or appear like a "forged" sample from another class. Our approach and goal are in stark contrast to common att…
A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness
State Key Laboratory for Novel Software Technology（计算机软件新技术全国重点实验室）；Nanjing University（南京大学）；School of Computer Science and Engineering（计算机科学与工程学院）；Southeast University（东南大学）
Recently, Convolutional Neural Networks (CNNs) demonstrate a considerable vulnerability to adversarial attacks, which can be easily misled by adversarial perturbations. With more aggressive methods proposed, adversarial attacks can be also applied to the physical world, causing practical issues to various CNN powered applications. To secure CNNs, adversarial attack detection is considered as the most critical approach. However, most existing works focus on superficial patterns and merely search a particular method to differentiate the adversarial inputs and natural inputs, ignoring the analysi…
Concept activation vectors: a unifying view and adversarial attacks
Department of Computer Science, Aalto University, Espoo, Finland（艾尔沃斯大学计算机科学系）；Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany（弗劳恩霍夫 Heinrich Hertz 研究所人工智能系）；Huawei Noah’s Ark Lab, Huawei Technologies, Paris, France（华为诺亚实验室）；Department of Electrical Engineering and Computer Science, Technical University Berlin, Germany（柏林技术大学电气工程与计算机科学系）
University of Maryland（马里兰大学）；GE Global Research（通用电气全球研究中心）；Avitas Systems（阿维塔斯系统公司）
Adversarial training has been shown to regularize deep neural networks in addition to increasing their robustness to adversarial examples. However, its impact on very deep state of the art networks has not been fully investigated. In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations as a regularizer during training. We use these perturbations to train very deep models such as ResNets and show improvement in performance both on adversarial and original test data. Our experiments highl…
In this paper, we analyze efficacy of the fast gradient sign method (FGSM) and the Carlini-Wagner's L2 (CW-L2) attack. We prove that, within a certain regime, the untargeted FGSM can fool any convolutional neural nets (CNNs) with ReLU activation; the targeted FGSM can mislead any CNNs with ReLU activation to classify any given image into any prescribed class. For a special two-layer neural network: a linear layer followed by the softmax output activation, we show that the CW-L2 attack increases the ratio of the classification probability between the target and ground truth classes. Moreover, w…
It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks larger, network architectural elements would otherwise matter little in improving adversarial robustness. Here we present evidence to challenge these common beliefs by a careful study about adversarial training. Our key observation is that the widely-used ReLU activation function significantly weakens adversarial training due to its non-smooth nature. Hence we propose smooth adversarial training (SAT), in which we re…
Peking University（北京大学）；University of Electronic Science and Technology of China（电子科技大学）；Australian National University（澳大利亚国立大学）
In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able to significantly improve CNN's generalization ability by adding carefully crafted noise into the intermediate layer activations. ANL and CANL can be easily implemented and integrated with most of the mainstream CNN-based models. We compared the effects of the different types of noise and visually demonstrate that our proposed adversarial noise instruct CNN models to learn to extract cleaner feature maps, which furth…
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems, detecting the presence of adversarial examples is of high practical relevance. By applying anomalous pattern detection techniques in the activation space of these models, we show that 2 of the recent and current state-of-the-art adversarial attacks on audio processing systems systematically lead to higher-than-expected activation at some subset of nodes and we…
ETH Zürich（苏黎世联邦理工学院）；University of Konstanz（康斯坦茨大学）；ETH AI Center（苏黎世联邦理工学院人工智能中心）
Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be safety-critic or impactful in the real world. We investigate the susceptibility of vision-based reinforcement learning agents to gradient-based adversarial attacks and evaluate a potential defense. We observe that Bottleneck Attention Modules (BAM) included in CNN architectures can act as potential tools to increase robustness against adversarial attacks. We show how learned atte…
Fudan University（复旦大学）；The University of Melbourne（墨尔本大学）
Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone small, carefully crafted perturbations, and which can easily fool a DNN into making misclassifications at test time. Thus far, the field of adversarial research has mainly focused on image models, under either a white-box setting, where an adversary has full access to model parameters, or a black-box setting where an adversary can only query the target model for probabilities or labels. Whilst several white-box attacks have been proposed for video models, black-box vide…
Princeton University（普林斯顿大学）；Institute for Advanced Study（高等研究院）
Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under natural conditions is still missing. Recently a convergence theory for standard (non-adversarial) supervised training was developed by various groups for {\em very overparametrized} nets. It is unclear how to extend these results to adversarial training because of the min-max objective. Recently, a first step towards this direction was made by Gao et al. using too…
University of California Santa Barbara（加州大学圣巴巴拉分校）
While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control over, the features being extracted. We report here on a promising neuro-inspired approach to DNNs with sparser and stronger activations. We use standard stochastic gradient training, supplementing the end-to-end discriminative cost function with layer-wise costs promoting Hebbian ("fire together," "wire together") updates for highly active neurons, and anti-Hebbian updates for the remaining neurons. Instead of batch no…
We propose a novel technique that can generate natural-looking adversarial examples by bounding the variations induced for internal activation values in some deep layer(s), through a distribution quantile bound and a polynomial barrier loss function. By bounding model internals instead of individual pixels, our attack admits perturbations closely coupled with the existing features of the original input, allowing the generated examples to be natural-looking while having diverse and often substantial pixel distances from the original input. Enforcing per-neuron distribution quantile bounds allow…
Recently, adversarial attacks can be applied to the physical world, causing practical issues to various Convolutional Neural Networks (CNNs) powered applications. Most existing physical adversarial attack defense works only focus on eliminating explicit perturbation patterns from inputs, ignoring interpretation to CNN's intrinsic vulnerability. Therefore, they lack the expected versatility to different attacks and thereby depend on considerable data processing costs. In this paper, we propose LanCe -- a comprehensive and lightweight CNN defense methodology against different physical adversaria…
The existence of adversarial examples poses a real danger when deep neural networks are deployed in the real world. The go-to strategy to quantify this vulnerability is to evaluate the model against specific attack algorithms. This approach is however inherently limited, as it says little about the robustness of the model against more powerful attacks not included in the evaluation. We develop a unified mathematical framework to describe relaxation-based robustness certification methods, which go beyond adversary-specific robustness evaluation and instead provide provable robustness guarantees…
A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
Carleton University（卡尔顿大学）；Computer Engineering Carleton University Ottawa, Canada（计算机工程系卡尔顿大学渥太华加拿大）；School of Information Technology Carleton University Ottawa, Canada（信息科技学院卡尔顿大学渥太华加拿大）
Technion – Israel Institute of Technology（以色列理工学院）；Intel – Artificial Intelligence Products Group (AIPG)（英特尔人工智能产品事业部）
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we extend the idea of adding white Gaussian noise to the network weights and activations during adversarial training (PNI) to the injection of colored noise for defense against common white-box and black-box attacks. We show that our approach outperforms PNI and various previous approaches in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets. In a…
We propose a method for improving adversarial robustness by addition of a new bounded function just before softmax. Recent studies hypothesize that small logits (inputs of softmax) by logit regularization can improve adversarial robustness of deep learning. Following this hypothesis, we analyze norms of logit vectors at the optimal point under the assumption of universal approximation and explore new methods for constraining logits by addition of a bounded function before softmax. We theoretically and empirically reveal that small logits by addition of a common activation function, e.g., hyper…
University of Washington（华盛顿大学）；UCSB（加州大学圣巴巴拉分校）；Adobe Research（奥多比研究院）；Yale University（耶鲁大学）
Adversarial training is a widely used strategy for making neural networks resistant to adversarial perturbations. For a neural network of width $m$, $n$ input training data in $d$ dimension, it takes $Ω(mnd)$ time cost per training iteration for the forward and backward computation. In this paper we analyze the convergence guarantee of adversarial training procedure on a two-layer neural network with shifted ReLU activation, and shows that only $o(m)$ neurons will be activated for each input data per iteration. Furthermore, we develop an algorithm for adversarial training with time cost $o(m n…
Yantai University（烟台大学）；Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）
It is well-known that deep neural networks are vulnerable to adversarial attacks. Recent studies show that well-designed classification parts can lead to better robustness. However, there is still much space for improvement along this line. In this paper, we first prove that, from a geometric point of view, the robustness of a neural network is equivalent to some angular margin condition of the classifier weights. We then explain why ReLU type function is not a good choice for activation under this framework. These findings reveal the limitations of the existing approaches and lead us to devel…
ICSI（国际计算机科学研究所）；University of California at Berkeley（加州大学伯克利分校）
It has been demonstrated that very simple attacks can fool highly-sophisticated neural network architectures. In particular, so-called adversarial examples, constructed from perturbations of input data that are small or imperceptible to humans but lead to different predictions, may lead to an enormous risk in certain critical applications. In light of this, there has been a great deal of work on developing adversarial training strategies to improve model robustness. These training strategies are very expensive, in both human and computational time. To complement these approaches, we propose a …
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Embry-Riddle Aeronautical University（安柏瑞德航空大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Tennessee at Martin（田纳西大学马丁分校）；Bowling Green State University（博林格林州立大学）；Old Dominion University（奥多明尼昂大学）
Deep Learning (DL) and Deep Neural Networks (DNNs) are widely used in various domains. However, adversarial attacks can easily mislead a neural network and lead to wrong decisions. Defense mechanisms are highly preferred in safety-critical applications. In this paper, firstly, we use the gradient class activation map (GradCAM) to analyze the behavior deviation of the VGG-16 network when its inputs are mixed with adversarial perturbation or Gaussian noise. In particular, our method can locate vulnerable layers that are sensitive to adversarial perturbation and Gaussian noise. We also show that …
It has been shown that deep learning models are vulnerable to adversarial attacks. We seek to further understand the consequence of such attacks on the intermediate activations of neural networks. We present an evaluation metric, POP-N, which scores the effectiveness of projecting data to N dimensions under the context of visualizing representations of adversarially perturbed inputs. We conduct experiments on CIFAR-10 to compare the POP-2 score of several dimensionality reduction algorithms across various adversarial attacks. Finally, we utilize the 2D data corresponding to high POP-2 scores t…
IBM Research（IBM研究院）；Carlson School of Management, University of Minnesota（明尼苏达大学卡尔森管理学院）
This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing an anomalous input. Detecting anomalies is a critical component for multiple machine learning problems including detecting adversarial noise. More broadly, this work is a step towards giving neural networks the ability to recognize an out-of-distribution sample. This is the first work to introduce "Subset Scanning" methods from the anomalous pattern detection domain to the task of detecting anomalous input of neural networks.…
Uber Advanced Technologies Group（优步先进技术集团）；Department of Computer Science, University of Toronto（多伦多大学计算机科学系）
We introduce a new framework for the exact point-wise $\ell_p$ robustness verification problem that exploits the layer-wise geometric structure of deep feed-forward networks with rectified linear activations (ReLU networks). The activation regions of the network partition the input space, and one can verify the $\ell_p$ robustness around a point by checking all the activation regions within the desired radius. The GeoCert algorithm (Jordan et al., NeurIPS 2019) treats this partition as a generic polyhedral complex in order to detect which region to check next. In contrast, our LayerCert framew…
Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the effect of different training losses, model sizes, activation functions, the addition of unlabeled data (through pseudo-labeling) and other factors on adversarial robustness. We discover that it is possible to train robust models that go well beyond state-of-the-art results by combining larger models, Swish/SiLU activations and model weight averaging. We demon…
In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation. And this defence strategy can be regarded as an activation function which can be applied to any kind of neural network. We also prove theoretically the effectiveness of this defense strategy under certain conditions. Besides, incorporating hidden layer representation we propose three types of adversarial attacks to generate three types of adversarial examples…
