paper-with-me

홈 › Papers

Crafting Data-free Universal Adversaries with Dilate Loss

2019-09-25 · Deepak Babu Sam, Abinaya K, Sudharsan K A, Venkatesh Babu Radhakrishnan

We introduce a method to create Universal Adversarial Perturbations (UAP) for a given CNN in a data-free manner. Data-free approaches suite scenarios where the original training data is unavailable for crafting adversaries. We show that the adversary generation with full training data can be approximated to a formulation without data. This is realized through a sequential optimization of the adversarial perturbation with the proposed dilate loss. Dilate loss basically maximizes the Euclidean norm of the output before nonlinearity at any layer. By doing so, the perturbation constrains the ReLU activation function at every layer to act roughly linear for data points and thus eliminate the dependency on data for crafting UAPs. Extensive experiments demonstrate that our method not only has theoretical support, but achieves higher fooling rate than the existing data-free work. Furthermore, we evidence improvement in limited data cases as well.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations

2018-01-24 · Konda Reddy Mopuri, Aditya Ganeshan, R. Venkatesh Babu

Machine learning models are susceptible to adversarial perturbations: small changes to input that can cause large changes in output. It is also demonstrated that there exist input-agnostic perturbations, called universal…

Adversarial AttackDepth EstimationObject RecognitionSemantic Segmentation

TRM-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Truncated Ratio Maximization

2023-01-01 · ICCV 2023 1 · Yiran Liu, Xin Feng, Yunlong Wang, Wu Yang 외

Aiming at crafting a single universal adversarial perturbation (UAP) to fool CNN models for various data samples, universal attack enables a more efficient and accurate evaluation for the robustness of CNN models. Ea…

Attacking Adversarial Defences by Smoothing the Loss Landscape

2022-08-01 · Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult …

Navigate

On the Robustness of Domain Constraints

2021-05-18 · Ryan Sheatsley, Blaine Hoak, Eric Pauley, Yohan Beugin 외

Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains …

valid

Adversarial Attacks on Neural Network Policies

2017-02-08 · Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan 외

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer visi…

Reinforcement Learning