Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have been reported, i.e., memorization effects induced by large loss data or because of small loss data and growing differences in loss distribution of training samples as the adversarial training progresses. Consequently, several mitigation approaches including early stopping, temporal ensembling and weight perturbations on small loss data have been proposed to mitigate the effect of robust overfitting. However, a side effect of these strategies is a larger reduction in clean accuracy compared to standard adversarial training. In this paper, we investigate if these mitigation approaches are complimentary to each other in improving adversarial training performance. We further propose the use of helper adversarial examples that can be obtained with minimal cost in the adversarial example generation, and show how they increase the clean accuracy in the existing approaches without compromising the robust accuracy.
相關內容
The state-of-the-art predictive maintenance (PdM) techniques have shown great success in reducing maintenance costs and downtime of complicated machines while increasing overall productivity through extensive utilization of Internet-of-Things (IoT) and Deep Learning (DL). Unfortunately, IoT sensors and DL algorithms are both prone to cyber-attacks. For instance, DL algorithms are known for their susceptibility to adversarial examples. Such adversarial attacks are vastly under-explored in the PdM domain. This is because the adversarial attacks in the computer vision domain for classification tasks cannot be directly applied to the PdM domain for multivariate time series (MTS) regression tasks. In this work, we propose an end-to-end methodology to design adversarially robust PdM systems by extensively analyzing the effect of different types of adversarial attacks and proposing a novel adversarial defense technique for DL-enabled PdM models. First, we propose novel MTS Projected Gradient Descent (PGD) and MTS PGD with random restarts (PGD_r) attacks. Then, we evaluate the impact of MTS PGD and PGD_r along with MTS Fast Gradient Sign Method (FGSM) and MTS Basic Iterative Method (BIM) on Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and Bi-directional LSTM based PdM system. Our results using NASA's turbofan engine dataset show that adversarial attacks can cause a severe defect (up to 11X) in the RUL prediction, outperforming the effectiveness of the state-of-the-art PdM attacks by 3X. Furthermore, we present a novel approximate adversarial training method to defend against adversarial attacks. We observe that approximate adversarial training can significantly improve the robustness of PdM models (up to 54X) and outperforms the state-of-the-art PdM defense methods by offering 3X more robustness.
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet malicious perturbations to natural inputs. These altered inputs are known in the literature as adversarial examples. In this paper, we propose a novel probabilistic framework to generalize and extend adversarial attacks in order to produce a desired probability distribution for the classes when we apply the attack method to a large number of inputs. This novel attack paradigm provides the adversary with greater control over the target model, thereby exposing, in a wide range of scenarios, threats against deep learning models that cannot be conducted by the conventional paradigms. We introduce four different strategies to efficiently generate such attacks, and illustrate our approach by extending multiple adversarial attack algorithms. We also experimentally validate our approach for the spoken command classification task and the Tweet emotion classification task, two exemplary machine learning problems in the audio and text domain, respectively. Our results demonstrate that we can closely approximate any probability distribution for the classes while maintaining a high fooling rate and even prevent the attacks from being detected by label-shift detection methods.
In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been thoroughly examined. In this study, we conduct the first comprehensive investigation of the robustness of leading camera-based 3D object detection methods under various adversarial conditions. Our experiments reveal five interesting findings: (a) the use of accurate depth estimation effectively improves robustness; (b) depth-estimation-free approaches do not show superior robustness; (c) bird's-eye-view-based representations exhibit greater robustness against localization attacks; (d) incorporating multi-frame benign inputs can effectively mitigate adversarial attacks; and (e) addressing long-tail problems can enhance robustness. We hope our work can provide guidance for the design of future camera-based object detection modules with improved adversarial robustness.
Neural retrieval models have acquired significant effectiveness gains over the last few years compared to term-based methods. Nevertheless, those models may be brittle when faced to typos, distribution shifts or vulnerable to malicious attacks. For instance, several recent papers demonstrated that such variations severely impacted models performances, and then tried to train more resilient models. Usual approaches include synonyms replacements or typos injections -- as data-augmentation -- and the use of more robust tokenizers (characterBERT, BPE-dropout). To further complement the literature, we investigate in this paper adversarial training as another possible solution to this robustness issue. Our comparison includes the two main families of BERT-based neural retrievers, i.e. dense and sparse, with and without distillation techniques. We then demonstrate that one of the most simple adversarial training techniques -- the Fast Gradient Sign Method (FGSM) -- can improve first stage rankers robustness and effectiveness. In particular, FGSM increases models performances on both in-domain and out-of-domain distributions, and also on queries with typos, for multiple neural retrievers.
Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial training that trains the model with adversarially perturbed samples instead of original ones. Various methods have been developed over recent years to improve adversarial training such as data augmentation or modifying training attacks. In this work, we examine the same problem from a new data-centric perspective. For this purpose, we first demonstrate that the existing model-based methods can be equivalent to applying smaller perturbation or optimization weights to the hard training examples. By using this finding, we propose detecting and removing these hard samples directly from the training procedure rather than applying complicated algorithms to mitigate their effects. For detection, we use maximum softmax probability as an effective method in out-of-distribution detection since we can consider the hard samples as the out-of-distribution samples for the whole data distribution. Our results on SVHN and CIFAR-10 datasets show the effectiveness of this method in improving the adversarial training without adding too much computational cost.
Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge graphs by encoding the concepts and relations into low-dimensional feature vector representations. The most effective representations for this task, called Knowledge Graph Embeddings (KGE), are learned through neural network architectures. Due to their impressive predictive performance, they are increasingly used in high-impact domains like healthcare, finance and education. However, are the black-box KGE models adversarially robust for use in domains with high stakes? This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph. To support this argument, two novel data poisoning attacks are proposed that craft input deletions or additions at training time to subvert the learned model's performance at inference time. These adversarial attacks target the task of predicting the missing facts in knowledge graphs using KGE models, and the evaluation shows that the simpler attacks are competitive with or outperform the computationally expensive ones. The thesis contributions not only highlight and provide an opportunity to fix the security vulnerabilities of KGE models, but also help to understand the black-box predictive behaviour of KGE models.
While existing work in robust deep learning has focused on small pixel-level $\ell_p$ norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations -- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. A network based on our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code and models will be made publicly available.
There is a recent large and growing interest in generative adversarial networks (GANs), which offer powerful features for generative modeling, density estimation, and energy function learning. GANs are difficult to train and evaluate but are capable of creating amazingly realistic, though synthetic, image data. Ideas stemming from GANs such as adversarial losses are creating research opportunities for other challenges such as domain adaptation. In this paper, we look at the field of GANs with emphasis on these areas of emerging research. To provide background for adversarial techniques, we survey the field of GANs, looking at the original formulation, training variants, evaluation methods, and extensions. Then we survey recent work on transfer learning, focusing on comparing different adversarial domain adaptation methods. Finally, we take a look forward to identify open research directions for GANs and domain adaptation, including some promising applications such as sensor-based human behavior modeling.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191