ترغب بنشر مسار تعليمي؟ اضغط هنا

Adversarial Distributional Training for Robust Deep Learning

170   0   0.0 ( 0 )
 نشر من قبل Yinpeng Dong
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. Besides, a single attack algorithm could be insufficient to explore the space of perturbations. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models. ADT is formulated as a minimax optimization problem, where the inner maximization aims to learn an adversarial distribution to characterize the potential adversarial examples around a natural one under an entropic regularizer, and the outer minimization aims to train robust models by minimizing the expected loss over the worst-case adversarial distributions. Through a theoretical analysis, we develop a general algorithm for solving ADT, and present three approaches for parameterizing the adversarial distributions, ranging from the typical Gaussian distributions to the flexible implicit ones. Empirical results on several benchmarks validate the effectiveness of ADT compared with the state-of-the-art AT methods.



قيم البحث

اقرأ أيضاً

Differentially private stochastic gradient descent (DPSGD) is a variation of stochastic gradient descent based on the Differential Privacy (DP) paradigm which can mitigate privacy threats arising from the presence of sensitive information in training data. One major drawback of training deep neural networks with DPSGD is a reduction in the models accuracy. In this paper, we propose an alternative method for preserving data privacy based on introducing noise through learnable probability distributions, which leads to a significant improvement in the utility of the resulting private models. We also demonstrate that normalization layers have a large beneficial impact on the performance of deep neural networks with noisy parameters. In particular, we show that contrary to general belief, a large amount of random noise can be added to the weights of neural networks without harming the performance, once the networks are augmented with normalization layers. We hypothesize that this robustness is a consequence of the scale invariance property of normalization operators. Building on these observations, we propose a new algorithmic technique for training deep neural networks under very low privacy budgets by sampling weights from Gaussian distributions and utilizing batch or layer normalization techniques to prevent performance degradation. Our method outperforms previous approaches, including DPSGD, by a substantial margin on a comprehensive set of experiments on Computer Vision and Natural Language Processing tasks. In particular, we obtain a 20 percent accuracy improvement over DPSGD on the MNIST and CIFAR10 datasets with DP-privacy budgets of $varepsilon = 0.05$ and $varepsilon = 2.0$, respectively. Our code is available online: https://github.com/uds-lsv/SIDP.
Despite the empirical success of using Adversarial Training to defend deep learning models against adversarial perturbations, so far, it still remains rather unclear what the principles are behind the existence of adversarial perturbations, and what adversarial training does to the neural network to remove them. In this paper, we present a principle that we call Feature Purification, where we show one of the causes of the existence of adversarial examples is the accumulation of certain small dense mixtures in the hidden weights during the training process of a neural network; and more importantly, one of the goals of adversarial training is to remove such mixtures to purify hidden weights. We present both experiments on the CIFAR-10 dataset to illustrate this principle, and a theoretical result proving that for certain natural classification tasks, training a two-layer neural network with ReLU activation using randomly initialized gradient descent indeed satisfies this principle. Technically, we give, to the best of our knowledge, the first result proving that the following two can hold simultaneously for training a neural network with ReLU activation. (1) Training over the original data is indeed non-robust to small adversarial perturbations of some radius. (2) Adversarial training, even with an empirical perturbation algorithm such as FGM, can in fact be provably robust against ANY perturbations of the same radius. Finally, we also prove a complexity lower bound, showing that low complexity models such as linear classifiers, low-degree polynomials, or even the neural tangent kernel for this network, CANNOT defend against perturbations of this same radius, no matter what algorithms are used to train them.
Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustness of the meta-learning model in few-shot learning. Although adversarial training (AT) methods such as Adversarial Query (AQ) can improve the adversarially robust performance of meta-learning models, AT is still computationally expensive training. On the other hand, meta-learning models trained with AT will drop significant accuracy on the original clean images. This paper proposed a meta-learning method on the adversarially robust neural network called Long-term Cross Adversarial Training (LCAT). LCAT will update meta-learning model parameters cross along the natural and adversarial sample distribution direction with long-term to improve both adversarial and clean few-shot classification accuracy. Due to cross-adversarial training, LCAT only needs half of the adversarial training epoch than AQ, resulting in a low adversarial training computation. Experiment results show that LCAT achieves superior performance both on the clean and adversarial few-shot classification accuracy than SOTA adversarial training methods for meta-learning models.
In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points. Unfortunately, one of the main issues in adversarial training is that robustness w.r.t. gradient-based attackers is always achieved at the cost of prediction accuracy. In this paper, a new algorithm, called Wasserstein Projected Gradient Descent (WPGD), for adversarial training is proposed. WPGD provides a simple way to obtain cost-sensitive robustness, resulting in a finer control of the robustness-accuracy trade-off. Moreover, WPGD solves an optimal transport problem on the output space of the network and it can efficiently discover directions where robustness is required, allowing to control the directional trade-off between accuracy and robustness. The proposed WPGD is validated in this work on image recognition tasks with different benchmark datasets and architectures. Moreover, real world-like datasets are often unbalanced: this paper shows that when dealing with such type of datasets, the performance of adversarial training are mainly affected in term of standard accuracy.
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to be challenging, and the method s relying on detecting adversarial samples are only valid when the attacker is oblivious to the detection mechanism. In this paper we first present an adversarial example detection method that provides performance guarantee to norm constrained adversaries. The method is based on the idea of training adversarial robust subspace detectors using asymmetrical adversarial training (AAT). The novel AAT objective presents a minimax problem similar to that of GANs; it has the same convergence property, and consequently supports the learning of class conditional distributions. We first demonstrate that the minimax problem could be reasonably solved by PGD attack, and then use the learned class conditional generative models to define generative detection/classification models that are both robust and more interpretable. We provide comprehensive evaluations of the above methods, and demonstrate their competitive performances and compelling properties on adversarial detection and robust classification problems.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا