اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدInterpreting Robust Optimization via Adversarial Influence Functions
221
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Robust optimization has been widely used in nowadays data science, especially in adversarial training. However, little research has been done to quantify how robust optimization changes the optimizers and the prediction losses comparing to standard training. In this paper, inspired by the influence function in robust statistics, we introduce the Adversarial Influence Function (AIF) as a tool to investigate the solution produced by robust optimization. The proposed AIF enjoys a closed-form and can be calculated efficiently. To illustrate the usage of AIF, we apply it to study model sensitivity -- a quantity defined to capture the change of prediction losses on the natural data after implementing robust optimization. We use AIF to analyze how model complexity and randomized smoothing affect the model sensitivity with respect to specific models. We further derive AIF for kernel regressions, with a particular application to neural tangent kernels, and experimentally demonstrate the effectiveness of the proposed AIF. Lastly, the theories of AIF will be extended to distributional robust optimization.
قيم البحث
اقرأ أيضاً
One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization. However, we demonstrate that loss surface in parameter space has no obvious relationship with gener
alization, especially under adversarial settings. Through visualizing decision surfaces in both parameter space and input space, we instead show that the geometry property of decision surface in input space correlates well with the adversarial robustness. We then propose an adversarial robustness indicator, which can evaluate a neural networks intrinsic robustness property without testing its accuracy under adversarial attacks. Guided by it, we further propose our robust training method. Without involving adversarial training, our method could enhance networks intrinsic adversarial robustness against various adversarial attacks.
Model selection requires repeatedly evaluating models on a given dataset and measuring their relative performances. In modern applications of machine learning, the models being considered are increasingly more expensive to evaluate and the datasets o
f interest are increasing in size. As a result, the process of model selection is time-consuming and computationally inefficient. In this work, we develop a model-specific data subsampling strategy that improves over random sampling whenever training points have varying influence. Specifically, we leverage influence functions to guide our selection strategy, proving theoretically, and demonstrating empirically that our approach quickly selects high-quality models.
This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task. We estimate attributions of different image regions to the decrease of the attacking cost based on the Shapley value. We define
and quantify interactions among adversarial perturbation pixels, and decompose the entire perturbation map into relatively independent perturbation components. The decomposition of the perturbation map shows that adversarially-trained DNNs have more perturbation components in the foreground than normally-trained DNNs. Moreover, compared to the normally-trained DNN, the adversarially-trained DNN have more components which mainly decrease the score of the true category. Above analyses provide new insights into the understanding of adversarial attacks.
We consider the problem of strongly-convex online optimization in presence of adversarial delays; in a T-iteration online game, the feedback of the players query at time t is arbitrarily delayed by an adversary for d_t rounds and delivered before the
game ends, at iteration t+d_t-1. Specifically for algo{online-gradient-descent} algorithm we show it has a simple regret bound of Oh{sum_{t=1}^T log (1+ frac{d_t}{t})}. This gives a clear and simple bound without resorting any distributional and limiting assumptions on the delays. We further show how this result encompasses and generalizes several of the existing known results in the literature. Specifically it matches the celebrated logarithmic regret Oh{log T} when there are no delays (i.e. d_t = 1) and regret bound of Oh{tau log T} for constant delays d_t = tau.
Recent researches have suggested that the predictive accuracy of neural network may contend with its adversarial robustness. This presents challenges in designing effective regularization schemes that also provide strong adversarial robustness. Revis
iting Vicinal Risk Minimization (VRM) as a unifying regularization principle, we propose Adversarial Labelling of Perturbed Samples (ALPS) as a regularization scheme that aims at improving the generalization ability and adversarial robustness of the trained model. ALPS trains neural networks with synthetic samples formed by perturbing each authentic input sample towards another one along with an adversarially assigned label. The ALPS regularization objective is formulated as a min-max problem, in which the outer problem is minimizing an upper-bound of the VRM loss, and the inner problem is L$_1$-ball constrained adversarial labelling on perturbed sample. The analytic solution to the induced inner maximization problem is elegantly derived, which enables computational efficiency. Experiments on the SVHN, CIFAR-10, CIFAR-100 and Tiny-ImageNet datasets show that the ALPS has a state-of-the-art regularization performance while also serving as an effective adversarial training scheme.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
