中文
相关论文

相关论文: Friendly Noise against Adversarial Noise: A Powerf…

200 篇论文

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

计算机视觉与模式识别 · 计算机科学 2020-09-04 Alex Serban , Erik Poll , Joost Visser

Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial…

计算机视觉与模式识别 · 计算机科学 2019-01-23 Long Zhang , Xuechao Sun , Yong Li , Zhenyu Zhang

Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense…

密码学与安全 · 计算机科学 2019-01-10 Bin Liang , Hongcheng Li , Miaoqiang Su , Xirong Li , Wenchang Shi , Xiaofeng Wang

From face recognition systems installed in phones to self-driving cars, the field of AI is witnessing rapid transformations and is being integrated into our everyday lives at an incredible pace. Any major failure in these system's…

密码学与安全 · 计算机科学 2020-12-14 Ayush Goel

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

机器学习 · 计算机科学 2019-07-08 Yuzhe Ma , Xiaojin Zhu , Justin Hsu

Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has…

机器学习 · 计算机科学 2021-11-11 Antonio Emanuele Cinà , Alessandro Torcinovich , Marcello Pelillo

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…

计算机视觉与模式识别 · 计算机科学 2018-12-21 Ziang Yan , Yiwen Guo , Changshui Zhang

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

机器学习 · 计算机科学 2024-03-21 Fabio De Gaspari , Dorjan Hitaj , Luigi V. Mancini

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

声音 · 计算机科学 2025-11-21 Aravindhan G , Yuvaraj Govindarajulu , Parin Shah

The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…

密码学与安全 · 计算机科学 2024-06-26 Mohamed Amine Merzouk , Erwan Beurier , Reda Yaich , Nora Boulahia-Cuppens , Frédéric Cuppens

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…

机器学习 · 计算机科学 2021-04-28 Sanjay Seetharaman , Shubham Malaviya , Rosni KV , Manish Shukla , Sachin Lodha

Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing tampered updates. Existing defenses often rely on impractical assumptions, such as access to…

机器学习 · 计算机科学 2025-02-25 Ehsan Hallaji , Roozbeh Razavi-Far , Mehrdad Saif

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be assessed through the…

密码学与安全 · 计算机科学 2021-04-06 Rehana Mahfuz , Rajeev Sahay , Aly El Gamal

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…

机器学习 · 计算机科学 2020-12-24 Aishan Liu , Xianglong Liu , Chongzhi Zhang , Hang Yu , Qiang Liu , Dacheng Tao

Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial…

计算机视觉与模式识别 · 计算机科学 2020-12-10 Mohammed Hassanin , Ibrahim Radwan , Nour Moustafa , Murat Tahtali , Neeraj Kumar

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Lin Li , Michael Spratling

Poisoning attacks have emerged as a significant security threat to machine learning algorithms. It has been demonstrated that adversaries who make small changes to the training set, such as adding specially crafted data points, can hurt the…

机器学习 · 计算机科学 2021-12-14 Samuel Deng , Sanjam Garg , Somesh Jha , Saeed Mahloujifar , Mohammad Mahmoody , Abhradeep Thakurta

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks. Despite the significant progress in the attack success rate that has been made recently, the adversarial noise generated by most of…

计算机视觉与模式识别 · 计算机科学 2023-10-17 Renyang Liu , Jinhong Zhang , Haoran Li , Jin Zhang , Yuanyu Wang , Wei Zhou

Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial…

机器学习 · 计算机科学 2019-11-22 Ilia Shumailov , Yiren Zhao , Robert Mullins , Ross Anderson