paper-with-me

Papers

SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations

2019-10-08 · Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi

Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properties or frequency-domain characteristics has not been sufficiently explored. In this paper, we study the smoothness of perturbations and propose SmoothFool, a general and computationally efficient framework for computing smooth adversarial perturbations. Through extensive experiments, we validate the efficacy of the proposed method for both the white-box and black-box attack scenarios. In particular, we demonstrate that: (i) there exist extremely smooth adversarial perturbations for well-established and widely used network architectures, (ii) smoothness significantly enhances the robustness of perturbations against state-of-the-art defense mechanisms, (iii) smoothness improves the transferability of adversarial perturbations across both data points and network architectures, and (iv) class categories exhibit a variable range of susceptibility to smooth perturbations. Our results suggest that smooth APs can play a significant role in exploring the vulnerability extent of DNNs to adversarial examples.

📄 PDF Abstract BibTeX arXiv:1910.03624

Code (1)

alldbi/SmoothFool 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Smoothed Embeddings for Certified Few-Shot Learning

2022-02-02 · Mikhail Pautov, Olesya Kuznetsova, Nurislam Tursynbek, Aleksandr Petiushko 외

Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not…

Adversarial RobustnessFew-Shot Learning

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

2024-07-16 · Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu 외

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized…

Adversarial Robustness

Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses

2026-06-18 · Zhuoyu Cheng, Kohei Hatano, Eiji Takimoto arxiv

We study adversarial bandit optimization in which the loss functions may be non-convex and non-smooth. In each round, the learner selects an action and observes only the loss incurred at that action. The loss consists of…

Discrete Randomized Smoothing Meets Quantum Computing

2024-08-01 · Tom Wollschläger, Aman Saxena, Nicola Franco, Jeanette Miriam Lorenz 외

Breakthroughs in machine learning (ML) and advances in quantum computing (QC) drive the interdisciplinary field of quantum machine learning to new levels. However, due to the susceptibility of ML models to adversarial at…

Quantum Machine Learning

Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis

2022-10-02 · Jiancong Xiao, Zeyu Qin, Yanbo Fan, Baoyuan Wu 외

Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of perturbation e.g., the $\ell_\infty$ attacks)…

Adversarial Robustness