From face recognition systems installed in phones to self-driving cars, the field of AI is witnessing rapid transformations and is being integrated into our everyday lives at an incredible pace. Any major failure in these system's predictions could be devastating, leaking sensitive information or even costing lives (as in the case of self-driving cars). However, deep neural networks, which form the basis of such systems, are highly susceptible to a specific type of attack, called adversarial attacks. A hacker can, even with bare minimum computation, generate adversarial examples (images or data points that belong to another class, but consistently fool the model to get misclassified as genuine) and crumble the basis of such algorithms. In this paper, we compile and test numerous approaches to defend against such adversarial attacks. Out of the ones explored, we found two effective techniques, namely Dropout and Denoising Autoencoders, and show their success in preventing such attacks from fooling the model. We demonstrate that these techniques are also resistant to both higher noise levels as well as different kinds of adversarial attacks (although not tested against all). We also develop a framework for deciding the suitable defense technique to use against attacks, based on the nature of the application and resource constraints of the Deep Neural Network.
MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.
Harbin Insititute of Technology（哈尔滨工业大学）；The University of Texas at Austin（得克萨斯大学奥斯汀分校）；Harbin Insititute of Technology(ShenZhen)（哈尔滨工业大学（深圳））；Macquaire University（麦考瑞大学）；University of Technology Sydney（悉尼科技大学）
Nowadays, Deep Learning as a service can be deployed in Internet of Things (IoT) to provide smart services and sensor data processing. However, recent research has revealed that some Deep Neural Networks (DNN) can be easily misled by adding relatively small but adversarial perturbations to the input (e.g., pixel mutation in input images). One challenge in defending DNN against these attacks is to efficiently identifying and filtering out the adversarial pixels. The state-of-the-art defense strategies with good robustness often require additional model training for specific attacks. To reduce t…
Under adversarial attacks, time series regression and classification are vulnerable. Adversarial defense, on the other hand, can make the models more resilient. It is important to evaluate how vulnerable different time series models are to attacks and how well they recover using defense. The sensitivity to various attacks and the robustness using the defense of several time series models are investigated in this study. Experiments are run on seven-time series models with three adversarial attacks and one adversarial defense. According to the findings, all models, particularly GRU and RNN, appe…
Adversarial attacks hamper the functionality and accuracy of Deep Neural Networks (DNNs) by meddling with subtle perturbations to their inputs.In this work, we propose a new Mask-based Adversarial Defense scheme (MAD) for DNNs to mitigate the negative effect from adversarial attacks. To be precise, our method promotes the robustness of a DNN by randomly masking a portion of potential adversarial images, and as a result, the %classification result output of the DNN becomes more tolerant to minor input perturbations. Compared with existing adversarial defense techniques, our method does not need…
As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have been proposed to improve robustness of deep learning software, many of them are ineffective against adaptive attacks. In this work, we propose a novel characterization to distinguish adversarial examples from benign ones based on the observation that adversarial examples are significantly less robust than benign ones. As existing robustness measurement does …
This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. First, we evaluate whether features learned through self-supervision are more robust to adversarial attacks than those emerging from supervised learning. Then, we present properties arising for attacks in the latent space. Finally, we evaluate whether three well-known defense strategies can increase adversarial robustness in downstream tasks by only fine-tuning the classification head to provide robustness even in view of limited compute resources. Thes…
Emergence of the utility of 3D point cloud data in safety-critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point c…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；TU Kaiserslautern（凯撒斯劳滕工业大学）
The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of the model itself rather than the modality. Several attempts have been made to defend against these adversarial attacks, particularly for the visual modality. In this paper, we perform detailed benchmarking of well-proven adversarial defense methodologies on time-series data. We restrict ourselves to the $L_{\infty}$ threat model. We also explore the trade-off between smoothness …
DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Tsinghua-Bosch Joint ML Center, Tsinghua University（清华大学-博世联合机器学习中心）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；Zhongguancun Laboratory（中关村实验室）；RealAI
A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification
School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University（拉夫堡大学沃尔森机械、电气与制造工程学院）；University of Cagliari（卡利亚里大学）；University of Genova（热那亚大学）
Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels (sentence / word / character), adversarial attacks can fool PrLMs to generate incorrect predictions, which questions the robustness of PrLMs. However, we find that most existing textual adversarial examples are unnatural, which can be easily distinguished by both human and machine. Based on a general anomaly detector, we propose a novel metric (Degree of Anoma…
Hong Kong Baptist University（香港浸会大学）；AWS AI Labs（AWS 人工智能实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）
Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while adversarial defense aims to defend the network against images with imperceptible adversarial perturbations. In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks. Furthermore, we show that adversarial defense mechanisms trained on known classes do not generalize well to open-set samples. Motivated by this observation, we empha…
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）
Department of Computer Engineering, University of Central Flordia（中佛罗里达大学计算机工程系）；Tencent AI Lab at Seattle（腾讯西雅图人工智能实验室）
Deep learning algorithms and networks are vulnerable to perturbed inputs which is known as the adversarial attack. Many defense methodologies have been investigated to defend against such adversarial attack. In this work, we propose a novel methodology to defend the existing powerful attack model. We for the first time introduce a new attacking scheme for the attacker and set a practical constraint for white box attack. Under this proposed attacking scheme, we present the best defense ever reported against some of the recent strong attacks. It consists of a set of nonlinear function to process…
This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimization-based attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining non-certified white-box-secure defenses at ICLR 2018, we find ob…
It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are crafted, for example, by calculating gradients of a carefully defined loss function with respect to the input. As a countermeasure, some researchers have tried to design robust models by blocking or obfuscating gradients, even in white-box settings. Another line of research proposes introducing a separate detector to attempt to detect adversarial examples. This a…
We have seen a surge in research aims toward adversarial attacks and defenses in AI/ML systems. While it is crucial to formulate new attack methods and devise novel defense strategies for robustness, it is also imperative to recognize who is responsible for implementing, validating, and justifying the necessity of these defenses. In particular, which components of the system are vulnerable to what type of adversarial attacks, and the expertise needed to realize the severity of adversarial attacks. Also how to evaluate and address the adversarial challenges in order to recommend defense strateg…
Evolving attacks on the vulnerabilities of the computing systems demand novel defense strategies to keep pace with newer attacks. This report discusses previous works on side-channel attacks (SCAs) and defenses for cache-targeted and physical proximity attacks. We then discuss the proposed Entropy-Shield as a defense against timing SCAs, and explain how we can extend the same to hardware-based implementations of crypto applications as "Entropy-Shield for FPGA". We then discuss why we want to build newer attacks with the hope of coming up with better defense strategies.
Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been proposed, and different researchers have made seemingly contradictory claims on their effectiveness. We present an analysis of possible adversarial models, and propose an evaluation framework for comparing different defense mechanisms. As part of the framework, we introduce a more powerful and realistic adversary strategy. Furthermore, we propose a new defense …
South China University of Technology（华南理工大学）；ETH Zürich（苏黎世联邦理工学院）；National University of Singapore（新加坡国立大学）
Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing defense methods focus on some specific types of adversarial examples and may fail to defend well in real-world applications. In practice, we may face many types of attacks where the exact type of adversarial examples in real-world applications can be even unknown. In this paper, motivated by that adversarial examples are more likely to appear near the classifica…
I introduce a very simple method to defend against adversarial examples. The basic idea is to raise the slope of the ReLU function at the test time. Experiments over MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed defense against a number of strong attacks in both untargeted and targeted settings. While perhaps not as effective as the state of the art adversarial defenses, this approach can provide insights to understand and mitigate adversarial attacks. It can also be used in conjunction with other defenses.
Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a new adversarial defense which is a defensive transform for both training and test images inspired by perceptual image encryption methods. The proposed method utilizes a block-wise pixel shuffling method with a secret key. The experiments are carried out on both adaptive and non-adaptive maximum-norm bounded white-box attacks while considering obfuscated gra…
We consider a cloud based multiserver system consisting of a set of replica application servers behind a set of proxy (indirection) servers which interact directly with clients over the Internet. We study a proactive moving-target defense to thwart a DDoS attacker's reconnaissance phase and consequently reduce the attack's impact. The defense is effectively a moving-target (motag) technique in which the proxies dynamically change. The system is evaluated using an AWS prototype of HTTP redirection and by numerical evaluations of an adversarial coupon-collector mathematical model, the latter all…
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended. Based on the design philosophy of ensemble of diverse weak defenses, we propose ATHENA---a flexible and extensible framework for building generic yet effective defenses against adversarial attacks. We have conducted a comprehensive empirical study to evaluate several realizations of ATHENA with four threat models including zero-knowledge, black-box, gray-box, and whi…
Adversarial examples are known to mislead deep learning models to incorrectly classify them, even in domains where such models achieve state-of-the-art performance. Until recently, research on both attack and defense methods focused on image recognition, primarily using convolutional neural networks (CNNs). In recent years, adversarial example generation methods for recurrent neural networks (RNNs) have been published, demonstrating that RNN classifiers are also vulnerable to such attacks. In this paper, we present a novel defense method, termed sequence squeezing, to make RNN classifiers more…
Black-box adversarial attacks generate adversarial samples via iterative optimizations using repeated queries. Defending deep neural networks against such attacks has been challenging. In this paper, we propose an efficient Boundary Defense (BD) method which mitigates black-box attacks by exploiting the fact that the adversarial optimizations often need samples on the classification boundary. Our method detects the boundary samples as those with low classification confidence and adds white Gaussian noise to their logits. The method's impact on the deep network's classification accuracy is anal…
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy multiple simultaneous constraints often over-optimize against one constraint at the cost of satisfying another. We introduce Orthogonal Projected Gradient Descent, an improved attack technique to generate adversarial examples that avoids this problem by orthogonalizing the gradients when running standard gradient-based attacks. We use our technique to evade fo…
Recently researchers have proposed using deep learning-based systems for malware detection. Unfortunately, all deep learning classification systems are vulnerable to adversarial attacks. Previous work has studied adversarial attacks against static analysis-based malware classifiers which only classify the content of the unknown file without execution. However, since the majority of malware is either packed or encrypted, malware classification based on static analysis often fails to detect these types of files. To overcome this limitation, anti-malware companies typically perform dynamic analys…
Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at test time. We propose dynamic defenses, to adapt the model and input during testing, by defensive entropy minimization (dent). Dent alters testing, but not training, for compatibility with existing models and train-time defenses. Dent improves the robustness of adversarially-trained defenses and nominally-trained models against white-box, black-box, and adap…
A recent defense proposes to inject "honeypots" into neural networks in order to detect adversarial attacks. We break the baseline version of this defense by reducing the detection true positive rate to 0\% and the detection AUC to 0.02, maintaining the original distortion bounds. The authors of the original paper have amended the defense in their CCS'20 paper to mitigate this attacks. To aid further research, we release the complete 2.5 hour keystroke-by-keystroke screen recording of our attack process at https://nicholas.carlini.com/code/ccs_honeypot_break.
University of Central Florida（中佛罗里达大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
The vulnerability of deep networks to adversarial attacks is a central problem for deep learning from the perspective of both cognition and security. The current most successful defense method is to train a classifier using adversarial images created during learning. Another defense approach involves transformation or purification of the original input to remove adversarial signals before the image is classified. We focus on defending naturally-trained classifiers using Markov Chain Monte Carlo (MCMC) sampling with an Energy-Based Model (EBM) for adversarial purification. In contrast to advers…
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of adversarial attacks. Based on our analysis on the performance of existing adversarial attacks, more adversarial perturbations are found in the mid and high-frequency components of input data. Therefore, by suppressing the high-frequency content in the training phase, the models robustness against adversarial examples is improved. Experiments showed that the pr…
In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work, we focus on the equally practical gray box setting, assuming an attacker has partial information. We propose a novel defense that assumes everything but a private key will be made available to the attacker. Our framework uses an image denoising procedure coupled with encryption via a discretized Baker map. Extensive testing against adversarial images (e.g. FGSM, PGD) crafted …
Several moving target defenses (MTDs) to counter adversarial ML attacks have been proposed in recent years. MTDs claim to increase the difficulty for the attacker in conducting attacks by regularly changing certain elements of the defense, such as cycling through configurations. To examine these claims, we study for the first time the effectiveness of several recent MTDs for adversarial ML attacks applied to the malware detection domain. Under different threat models, we show that transferability and query attack strategies can achieve high levels of evasion against these defenses through exis…
Shenzhen Youjia Innov Tech Co., Ltd（深圳佑驾创新科技有限公司）；South China University of Technology（华南理工大学）；Hong Kong University of Science and Technology（香港科技大学）
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks that would trigger misclassification of DNNs but may be imperceptible to human perception. Adversarial defense has been an important way to improve the robustness of DNNs. Existing attack methods often construct adversarial examples relying on some metrics like the $\ell_p$ distance to perturb samples. However, these metrics can be insufficient to conduct adversarial attacks due to their limited perturbations. In this paper, we propose a new internal Wasserstein distance (IWD) to capture the semantic similarity of tw…
Deep Neural Networks (DNNs) are vulnerable to adversarial examples which would inveigle neural networks to make prediction errors with small perturbations on the input images. Researchers have been devoted to promoting the research on the universal adversarial perturbations (UAPs) which are gradient-free and have little prior knowledge on data distributions. Procedural adversarial noise attack is a data-free universal perturbation generation method. In this paper, we propose two universal adversarial perturbation (UAP) generation methods based on procedural noise functions: Simplex noise and W…
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic features of the input and filter the non-semantic perturbation. FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping between the high-dimensional data space and the low-dimensional semantic space; also mutual information is …
Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold conjecture has inspired a novel line of defenses against adversarial attacks on images. In this study, we find a similar phenomenon occurs in the contextualized embedding space induced by pretrained language models, in which adversarial texts tend to have their embeddings diverge from the manifold of natural ones. Based on this finding, we propose Textual Manif…
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）
École de Technologie Supérieure (ÉTS), Université du Québec（魁北克大学高等技术学院）
This paper proposes a new defense approach for counteracting state-of-the-art white and black-box adversarial attack algorithms. Our approach fits into the implicit reactive defense algorithm category since it does not directly manipulate the potentially malicious input signals. Instead, it reconstructs a similar signal with a synthesized spectrogram using a cyclic generative adversarial network. This cyclic framework helps to yield a stable generative model. Finally, we feed the reconstructed signal into the speech-to-text model for transcription. The conducted experiments on targeted and non…
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）
Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.
University of Tübingen（图宾根大学）；DeepMind（深度思维）；Everyday Robots（日常机器人公司）
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness. We categorize such adaptive test-time defenses, explain their potential benefits and drawbacks, and evaluate a representative variety of the latest adaptive defenses for image classification. Unfortunately, none significantly improve upon static defenses when subjected to our careful case study evaluation. Some even weaken the underlying static model while simultaneously increasing inference computation. While these results are disappointing, we still believe that adaptive test-time defenses are a promis…
Guangzhou University（广州大学）；Cyberspace Institute of Advanced Technology（网络空间先进技术研究院）
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually make assumptions about the adversarial example and attack method (e.g., the word frequency of the adversarial example, the perturbation level of the attack method). However, this limits the applicability of the detection method. To this end, we propose TREATED, a universal adversarial detection method that can defend against attacks of various pert…
