中文
相关论文

相关论文: Origins of Low-dimensional Adversarial Perturbatio…

200 篇论文

The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single…

机器学习 · 计算机科学 2022-04-20 Chaoning Zhang , Philipp Benz , Chenguo Lin , Adil Karjauv , Jing Wu , In So Kweon

Deep neural networks have achieved remarkable success in a wide range of classification tasks. However, they remain highly susceptible to adversarial examples - inputs that are subtly perturbed to induce misclassification while appearing…

机器学习 · 计算机科学 2025-10-20 Virendra Nishad , Bhaskar Mukhoty , Hilal AlQuabeh , Sandeep K. Shukla , Sayak Ray Chowdhury

We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generated by projected gradient descent exhibit two human-aligned…

机器学习 · 计算机科学 2022-01-03 Sung Min Park , Kuo-An Wei , Kai Xiao , Jerry Li , Aleksander Madry

Universal Adversarial Perturbations (UAPs) are imperceptible, image-agnostic vectors that cause deep neural networks (DNNs) to misclassify inputs with high probability. In practical attack scenarios, adversarial perturbations may undergo…

机器学习 · 计算机科学 2023-06-07 Changming Xu , Gagandeep Singh

Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input…

Adversarial perturbations have drawn great attentions in various deep neural networks. Most of them are computed by iterations and cannot be interpreted very well. In contrast, little attentions are paid to basic machine learning models…

机器学习 · 计算机科学 2022-04-08 Wen Su , Qingna Li , Chunfeng Cui

Deep reinforcement learning (DRL) is vulnerable to adversarial perturbations. Adversaries can mislead the policies of DRL agents by perturbing the state of the environment observed by the agents. Existing attacks are feasible in principle,…

机器学习 · 计算机科学 2022-09-26 Buse G. A. Tekgul , Shelly Wang , Samuel Marchal , N. Asokan

The vulnerability of Convolutional Neural Networks (CNNs) to adversarial samples has recently garnered significant attention in the machine learning community. Furthermore, recent studies have unveiled the existence of universal adversarial…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Juanjuan Weng , Zhiming Luo , Dazhen Lin , Shaozi Li

Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data. They are a class of attacks that represents a significant threat as they facilitate realistic, practical, and low-cost…

机器学习 · 计算机科学 2021-09-14 Kenneth T. Co , David Martinez Rego , Emil C. Lupu

We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding such perturbations.…

Adversarial perturbations are critical for certifying the robustness of deep learning models. A universal adversarial perturbation (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an…

机器学习 · 计算机科学 2022-08-19 Pu Zhao , Parikshit Ram , Songtao Lu , Yuguang Yao , Djallel Bouneffouf , Xue Lin , Sijia Liu

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in…

机器学习 · 计算机科学 2020-10-20 Honglin Li , Yifei Fan , Frieder Ganz , Anthony Yezzi , Payam Barnaghi

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

机器学习 · 计算机科学 2019-12-03 Tejus Gupta , Abhishek Sinha , Nupur Kumari , Mayank Singh , Balaji Krishnamurthy

Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples,…

音频与语音处理 · 电气工程与系统科学 2020-04-08 Jiguo Li , Xinfeng Zhang , Chuanmin Jia , Jizheng Xu , Li Zhang , Yue Wang , Siwei Ma , Wen Gao

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…

计算机视觉与模式识别 · 计算机科学 2017-03-10 Seyed-Mohsen Moosavi-Dezfooli , Alhussein Fawzi , Omar Fawzi , Pascal Frossard

Deep Neural Networks (DNNs) are vulnerable to adversarial examples which would inveigle neural networks to make prediction errors with small perturbations on the input images. Researchers have been devoted to promoting the research on the…

机器学习 · 计算机科学 2021-08-30 Jun Yan , Xiaoyang Deng , Huilin Yin , Wancheng Ge

Robustness is a key requirement for widespread deployment of machine learning algorithms, and has received much attention in both statistics and computer science. We study a natural model of robustness for high-dimensional statistical…

机器学习 · 计算机科学 2020-06-03 Pranjal Awasthi , Xue Chen , Aravindan Vijayaraghavan

In recent years there has been significant interest in the effect of different types of adversarial perturbations in data classification problems. Many of these models incorporate the adversarial power, which is an important parameter with…

偏微分方程分析 · 数学 2025-11-11 Rachel Morris , Ryan Murray

Universal adversarial perturbation (UAP), also known as image-agnostic perturbation, is a fixed perturbation map that can fool the classifier with high probabilities on arbitrary images, making it more practical for attacking deep models in…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Yihao Huang , Qing Guo , Felix Juefei-Xu , Ming Hu , Xiaojun Jia , Xiaochun Cao , Geguang Pu , Yang Liu

Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the…

密码学与安全 · 计算机科学 2024-08-06 Liang-bo Ning , Zeyu Dai , Wenqi Fan , Jingran Su , Chao Pan , Luning Wang , Qing Li
‹ 上一页 1 2 3 10 下一页 ›