Graph convolutional neural networks, which learn aggregations over neighbor nodes, have achieved great performance in node classification tasks. However, recent studies reported that such graph convolutional node classifier can be deceived by adversarial perturbations on graphs. Abusing graph convolutions, a node's classification result can be influenced by poisoning its neighbors. Given an attributed graph and a node classifier, how can we evaluate robustness against such indirect adversarial attacks? Can we generate strong adversarial perturbations which are effective on not only one-hop neighbors, but more far from the target? In this paper, we demonstrate that the node classifier can be deceived with high-confidence by poisoning just a single node even two-hops or more far from the target. Towards achieving the attack, we propose a new approach which searches smaller perturbations on just a single node far from the target. In our experiments, our proposed method shows 99% attack success rate within two-hops from the target in two datasets. We also demonstrate that m-layer graph convolutional neural networks have chance to be deceived by our indirect attack within m-hop neighbors. The proposed attack can be used as a benchmark in future defense attempts to develop graph convolutional neural networks with having adversary robustness.
University of Melbourne（墨尔本大学）；Northrop Grumman Corporation（诺斯罗普·格鲁曼公司）
Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions. Previous works that attempt to address this problem rely on assumptions about the nature of the attack/attacker or overestimate the knowledge of the learner, making them impractical. We introduce a novel Local Intrinsic Dimensionality (LID) based measure called N-LID that measures the local deviation of a given data point's LID with respect to its neighbors. We t…
Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the attacker desires. The key idea of state-of-the-art certified defenses against data poisoning attacks and backdoor attacks is to create a majority vote mechanism to predict the label of a testing example. Moreover, each voter is a base classifier trained on a subset of the training dataset. Classical simple learning algorithms such as k nearest neighbors (kN…
Sun Yat-Sen University（中山大学）；South China University of Technology（华南理工大学）
Nowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighbourhood-based collaborative filtering is common and effective. To date, despite its effectiveness, there has been little effort to explore their robustness and the impact of data poisoning attacks on their performance. Can the neighbourhood-based recommender systems be easily fooled? To this end, we shed light on the robustness of neighbourhood-based recommender systems and propose a novel data poisoning attack framework encoding the purpose of attack and constrain…
University of California Merced（加州大学默塞德分校）；Tagliatela College of Engineering（塔利亚泰拉工程学院）；University of New Haven（纽黑文大学）
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques that are only applicable to specific machine learning models. Additionally, the existing data poisoning attacks in the literature are limited to either binary classifiers or to gradient-based algorithms. To address these limitations, this paper first proposes a novel model-free label-flipping attack based on the multi-modality of the data, in which the adversar…
Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years, interest has surged in adversarial attacks on graphs yet the Graph Classification setting remains nearly untouched. Since a Graph Classification dataset consists of discrete graphs with class labels, related work has forgone direct gradient optimization in favor of an indirect Reinforcement Learning approach. We will study the novel problem of Data Poisoning …
Attacks on machine learning models have been, since their conception, a very persistent and evasive issue resembling an endless cat-and-mouse game. One major variant of such attacks is poisoning attacks which can indirectly manipulate an ML model. It has been observed over the years that the majority of proposed effective defense models are only effective when an attacker is not aware of them being employed. In this paper, we show that the attack-agnostic De-Pois defense is hardly an exception to that rule. In fact, we demonstrate its vulnerability to the simplest White-Box and Black-Box attac…
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Rochester（罗切斯特大学）
Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can provide privacy, security and economic benefits by designing an effective communication protocol. However, the communication protocol amongst different nodes could be exploited by attackers to launch data poisoning attacks, which has been demonstrated as a big threat to most machine learning models. In this paper, we attempt to explore the vulnerability of federated machine learning. More specifically, we focus on at…
Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
Center for Data Science, Zhejiang University, Hangzhou 310000, China（数据科学中心，浙江大学，杭州）；College of Computer Science, Zhejiang University, Hangzhou 310000, China（计算机科学学院，浙江大学，杭州）
Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter out anomalous training points before training the model. In this paper, we develop three attacks that can bypass a broad range of common data sanitization defenses, including anomaly detectors based on nearest neighbors, training loss, and singular-value decomposition. By adding just 3% poisoned data, our attacks successfully increase test error on the Enro…
Western Washington University（西华盛顿大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of an ML model, whereas backdoor data poisoning attacks maintain system performance unless the ML model is presented with an input containing an embedded "trigger" that provides a predetermined response advantageous to the adversary. Our work builds upon prior backdoor data-poisoning research for ML image classifiers and systematically assesses different exper…
The heterogeneous network is a robust data abstraction that can model entities of different types interacting in various ways. Such heterogeneity brings rich semantic information but presents nontrivial challenges in aggregating the heterogeneous relationships between objects - especially those of higher-order indirect relations. Recent graph neural network approaches for representation learning on heterogeneous networks typically employ the attention mechanism, which is often only optimized for predictions based on direct links. Furthermore, even though most deep learning methods can aggregat…
Mississippi State University（密西西比州立大学）；University of South Florida（南佛罗里达大学）；University of Oklahoma（俄克拉荷马大学）
Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network. Though FL enables a privacy-preserving mobile edge computing framework using IoT devices, recent studies have shown that this approach is susceptible to poisoning attacks from the side of remote clients. To address the poisoning attacks on FL, we provide a \textit{two-phase} defense algorithm called {Lo}cal {Ma}licious Facto{r} (LoMar). In phase I, LoMar scores model updates from each remote client by measuring the relative dist…
Robert Morris University（罗伯特·莫里斯大学）；Southern Illinois University（南伊利诺伊大学）；Louisiana State University Shreveport（路易斯安那州立大学什里夫波特分校）
Human Activity Recognition (HAR) is a problem of interpreting sensor data to human movement using an efficient machine learning (ML) approach. The HAR systems rely on data from untrusted users, making them susceptible to data poisoning attacks. In a poisoning attack, attackers manipulate the sensor readings to contaminate the training set, misleading the HAR to produce erroneous outcomes. This paper presents the design of a label flipping data poisoning attack for a HAR system, where the label of a sensor reading is maliciously changed in the data collection phase. Due to high noise and uncert…
Tulane University（杜兰大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；IBM Research（IBM研究院）
Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality in achieving high certified adversarial robustness. Specifically, we propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers. Unlike other poisoning attacks that reduce the accuracy of the poisoned models on a small …
University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Amherst College（阿默斯特学院）
Nearest neighbor-based methods are commonly used for classification tasks and as subroutines of other data-analysis methods. An attacker with the capability of inserting their own data points into the training set can manipulate the inferred nearest neighbor structure. We distill this goal to the task of performing a training-set data insertion attack against $k$-Nearest Neighbor classification ($k$NN). We prove that computing an optimal training-time (a.k.a. poisoning) attack against $k$NN classification is NP-Hard, even when $k = 1$ and the attacker can insert only a single data point. We pr…
Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learning
School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；School of Engineering and Applied Science, Harvard University（哈佛大学工程与应用科学学院）；Department of Electrical and Electronic Engineering, Imperial College London（伦敦帝国理工学院电子与电气工程系）
Beijing University of Posts and Telecommunications（北京邮电大学）；Beihang University（北京航空航天大学）；The Hong Kong University of Science and Technology（香港科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
University of Louisville（路易斯维尔大学）；North Carolina State University（北卡罗来纳州立大学）；University of Wisconsin-Whitewater（威斯康星大学怀特沃特分校）；Wayne State University（韦恩州立大学）；The Ohio State University（俄亥俄州立大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Duke University（杜克大学）
Informatics Institute（信息学研究所）；University of Amsterdam（阿姆斯特丹大学）
Earlier approaches indirectly studied the information captured by the hidden states of recurrent and non-recurrent neural machine translation models by feeding them into different classifiers. In this paper, we look at the encoder hidden states of both transformer and recurrent machine translation models from the nearest neighbors perspective. We investigate to what extent the nearest neighbors share information with the underlying word embeddings as well as related WordNet entries. Additionally, we study the underlying syntactic structure of the nearest neighbors to shed light on the role of …
Pennsylvania State University（宾夕法尼亚州立大学）；McGill University（麦吉尔大学）
Data samples collected for training machine learning models are typically assumed to be independent and identically distributed (iid). Recent research has demonstrated that this assumption can be problematic as it simplifies the manifold of structured data. This has motivated different research areas such as data poisoning, model improvement, and explanation of machine learning models. In this work, we study the influence of a sample on determining the intrinsic topological features of its underlying manifold. We propose the Shapley Homology framework, which provides a quantitative metric for …
Northeastern University（东北大学）；Army Research Laboratory（陆军研究实验室）
Vertex classification is vulnerable to perturbations of both graph topology and vertex attributes, as shown in recent research. As in other machine learning domains, concerns about robustness to adversarial manipulation can prevent potential users from adopting proposed methods when the consequence of action is very high. This paper considers two topological characteristics of graphs and explores the way these features affect the amount the adversary must perturb the graph in order to be successful. We show that, if certain vertices are included in the training set, it is possible to substanti…
Quantifying the topological similarities of different parts of urban road networks (URNs) enables us to understand the urban growth patterns. While conventional statistics provide useful information about characteristics of either a single node's direct neighbors or the entire network, such metrics fail to measure the similarities of subnetworks considering local indirect neighborhood relationships. In this study, we propose a graph-based machine-learning method to quantify the spatial homogeneity of subnetworks. We apply the method to 11,790 urban road networks across 30 cities worldwide to m…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Airbnb, Inc（爱彼迎公司）；UC San Diego（加州大学圣地亚哥分校）；Walmart Labs（沃尔玛实验室）
Within-basket recommendation reduces the exploration time of users, where the user's intention of the basket matters. The intent of a shopping basket can be retrieved from both user-item collaborative filtering signals and multi-item correlations. By defining a basket entity to represent the basket intent, we can model this problem as a basket-item link prediction task in the User-Basket-Item~(UBI) graph. Previous work solves the problem by leveraging user-item interactions and item-item interactions simultaneously. However, collectivity and heterogeneity characteristics are hardly investigate…
