中文
相关论文

相关论文: Near-Optimal Evasion of Convex-Inducing Classifier…

200 篇论文

Classifiers are often used to detect miscreant activities. We study how an adversary can systematically query a classifier to elicit information that allows the adversary to evade detection while incurring a near-minimal cost of modifying…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

密码学与安全 · 计算机科学 2017-08-22 Battista Biggio , Igino Corona , Davide Maiorca , Blaine Nelson , Nedim Srndic , Pavel Laskov , Giorgio Giacinto , Fabio Roli

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an…

计算机视觉与模式识别 · 计算机科学 2010-08-24 Chunhua Shen , Peng Wang , Anton van den Hengel

We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online. Unlike traditional bounds which seek to minimize the misclassification rate, we minimize the…

机器学习 · 计算机科学 2021-11-17 Guru Guruganesh , Allen Liu , Jon Schneider , Joshua Wang

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an…

计算机视觉与模式识别 · 计算机科学 2013-01-11 Chunhua Shen , Peng Wang , Sakrapee Paisitkriangkrai , Anton van den Hengel

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

机器学习 · 计算机科学 2022-06-17 Florian Tramèr

We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data. For previously unseen examples, the approach is guaranteed to detect all adversarial…

机器学习 · 计算机科学 2018-06-12 Eric Wong , J. Zico Kolter

Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…

密码学与安全 · 计算机科学 2026-04-24 Pawan Acharya , Lan Zhang

Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply by training on a non-overlapping set of classes. This can…

机器学习 · 计算机科学 2021-10-26 Yi Xiang Marcus Tan , Penny Chong , Jiamei Sun , Ngai-man Cheung , Yuval Elovici , Alexander Binder

In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation. In…

机器学习 · 统计学 2016-08-11 Aditi Raghunathan , Roy Frostig , John Duchi , Percy Liang

Machine-learning based intrusion detection classifiers are able to detect unknown attacks, but at the same time, they may be susceptible to evasion by obfuscation techniques. An adversary intruder which possesses a crucial knowledge about a…

密码学与安全 · 计算机科学 2019-04-16 Ivan Homoliak , Martin Teknos , Martín Ochoa , Dominik Breitenbacher , Saeid Hosseini , Petr Hanacek

Decision-based evasion attacks repeatedly query a black-box classifier to generate adversarial examples. Prior work measures the cost of such attacks by the total number of queries made to the classifier. We argue this metric is flawed.…

密码学与安全 · 计算机科学 2024-02-15 Edoardo Debenedetti , Nicholas Carlini , Florian Tramèr

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models.…

机器学习 · 统计学 2019-10-08 Gavin S. Hartnett , Andrew J. Lohn , Alexander P. Sedlack

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks…

机器学习 · 计算机科学 2021-04-22 Fnu Suya , Saeed Mahloujifar , Anshuman Suri , David Evans , Yuan Tian

Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…

机器学习 · 计算机科学 2019-06-03 Rangeet Pan , Md Johirul Islam , Shibbir Ahmed , Hridesh Rajan

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…

计算机视觉与模式识别 · 计算机科学 2017-10-30 Xin Li , Fuxin Li

Network operators are generally aware of common attack vectors that they defend against. For most networks the vast majority of traffic is legitimate. However new attack vectors are continually designed and attempted by bad actors which…

机器学习 · 计算机科学 2019-04-03 Amir Ziai

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

机器学习 · 计算机科学 2022-06-24 Haojing Shen , Sihong Chen , Ran Wang , Xizhao Wang

In recent years, a certain type of problems have become of interest where one wants to query a trained classifier. Specifically, one wants to find the closest instance to a given input instance such that the classifier's predicted label is…

机器学习 · 计算机科学 2026-03-20 Miguel Á. Carreira-Perpiñán , Suryabhan Singh Hada

Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate…

密码学与安全 · 计算机科学 2017-05-26 Yi Han , Benjamin I. P. Rubinstein
‹ 上一页 1 2 3 10 下一页 ›