Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
University of Maryland（马里兰大学）；Massachussetts Institute of Technology（麻省理工学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Berkeley（加利福尼亚大学伯克利分校）
Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy human supervision over the data collection process exposes organizations to security vulnerabilities; training data can be manipulated to control and degrade the downstream behaviors of learned models. The goal of this work is to systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space. In addition to describing various poisoning and backdoor threat models and the relationships among them, we develop their unified taxonomy.
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
Nanjing University of Information Science and Technology（南京信息工程大学）；University of Science and Technology of China（中国科学技术大学）；Huawei Technologies Co. Ltd.（华为技术有限公司）；Huazhong University of Science and Technology（华中科技大学）；China Academic of Electronics and Information Technology（中国电子信息产业发展研究院）
SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Tsinghua University（清华大学）；Jinan University（暨南大学）
Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt some external training data from an untrusted third party, a robust backdoor defense strategy during the training stage is of importance. We argue that the core of training-time defense is to select poisoned samples and to handle them properly. In this work, we summarize the training-time defenses from a unified framework as splitting the poisoned dataset into two data pools. Under our framework, we propose an adaptively split…
APBench: A Unified Benchmark for Availability Poisoning Attacks and Defenses
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Macau（澳门大学）
SoK: The Last Line of Defense: On Backdoor Defense Evaluation
University of Bergen（卑尔根大学）；Radboud University（拉德博德大学）；Delft University of Technology（代尔夫特理工大学）；University of Pavia（帕维亚大学）；Ikerlan Research Center Radboud University（Ikerlan研究中心拉德博德大学）
Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model stealing to adversarial attacks. However, it remains unclear exactly how dangerous poisoning methods are and which ones are more effective considering that these methods, even ones with identical objectives, have not been tested in consistent or realistic settings. We observe that data poisoning and backdoor attacks are highly sensitive to variations in the t…
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…
University of Maryland, College Park（马里兰大学帕克分校）；University of Siegen（锡根大学）
Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals revealed heightened fear in the private sector regarding data poisoning. Many previous defenses against poisoning either fail in the face of increasingly strong attacks, or they significantly degrade performance. However, we find that strong data augmentations, such as mixup and CutMix, can significantly diminish the threat of poisoning and backdoor attacks without trading off performance. We further verify the effective…
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many security-sensitive applications like payment apps. Such usages of deep learning systems provide the adversaries with sufficient incentives to perform attacks against these systems for their adversarial purposes. In this work, we consider a new type of attacks, called backdoor attacks, where the attacker's goal is to create a backdoor into a learning-based a…
Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There, we apply a $k$-means clustering algorithm on heatmaps produced by the state-of-the-art explainable AI method Layer-wise relevance propagation. The goal is to separate poisoned from un-poisoned data in the dataset. We compare this method with a similar method, called Activation Clustering, which also uses $k$-means clustering but applies it on the activation…
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；JD Explore Academy（京东探索研究院）；Tencent AI Lab（腾讯人工智能实验室）
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…
A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually a pattern that is either imperceptible or innocuous) and which are mislabeled to the attacker's target class. When trained on a backdoor-poisoned dataset, a DNN behaves normally on most benign test samples but makes incorrect predictions to the target class when the test sample has the backdoor pattern incorporated (i.e., contains a backdoor trigger). Here …
Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of the corrupted samples, the corruption of the training set must be as stealthy as possible. Previous works have focused on the stealthiness of the perturbation injected into the training samples, however they all assume that the labels of the corrupted samples are also poisoned. This greatly reduces the stealthiness of the attack, since samples whose content…
Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the unlabeled training samples, making them tempting targets for data poisoning attacks. In this paper we investigate the vulnerabilities of semi-supervised learning methods to backdoor data poisoning attacks on the unlabeled samples. We show that simple poisoning attacks that influence the distribution of the poisoned samples' predicted labels are highly effective - a…
Princeton University（普林斯顿大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only modifying a few training data, without controlling the training process. Currently, a tangible signature has been widely observed across a diverse set of backdoor poisoning attacks -- models trained on a poisoned dataset tend to learn separable latent representations for poison and clean samples. This latent separation is so pervasive that a family of backdoor defenses directly take it as a default assumption (dubbe…
Toyota Technological Institute Chicago（芝加哥丰田技术研究所）
A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical data; however, the model reliably errs on watermarked examples. To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. We then use this to analyze important statistical and computational issues surrounding…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；The Pennsylvania State University（宾夕法尼亚州立大学）
The black-box nature of deep neural networks (DNNs) facilitates attackers to manipulate the behavior of DNN through data poisoning. Being able to detect and mitigate poisoning attacks, typically categorized into backdoor and adversarial poisoning (AP), is critical in enabling safe adoption of DNNs in many application domains. Although recent works demonstrate encouraging results on detection of certain backdoor attacks, they exhibit inherent limitations which may significantly constrain the applicability. Indeed, no technique exists for detecting AP attacks, which represents a harder challenge…
University of Maryland（马里兰大学）；University of Siegen（锡根大学）
Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes with a sharp decrease in model performance. The InstaHide method has recently been proposed as an alternative to DP training that leverages supposed privacy properties of the mixup augmentation, although without rigorous guarantees. In this work, we show that strong data augmentations, such as mixup and random additive noise, nullify poison attacks while enduring only a small a…
University of Alberta（阿尔伯塔大学）；Illinois Institute of Technology（伊利诺伊理工学院）；Michigan State University（密歇根州立大学）
Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in downstream tasks. The stealthiness of backdoor attacks has imposed tremendous defense challenges in today's machine learning paradigm. In this paper, we explore the potential of self-training via additional unlabeled data for mitigating backdoor attacks. We begin by making a pilot study to show that vanilla self-training is not effective in backdoor mitigatio…
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；National Computer network Emergency Response technical Team/Coordination Center of China（国家计算机网络应急技术处理协调中心）
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
University of West Florida（西佛罗里达大学）；Florida Institute For Human and Machine Cognition (IHMC)（佛罗里达人机认知研究所）；Center for Cybersecurity, University of West Florida（西佛罗里达大学网络安全中心）
Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor and poisoning attacks a significant threat. By poisoning just 0.01% of a dataset (e.g., just 300 images of the 3 million-example Conceptual Captions dataset), we can cause the model to misclassify test images by overlaying a small patch. Targeted poisoning attacks, whereby the model misclassifies a particular test input with an adversarially-desired label, ar…
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；Nanyang Technological University（南洋理工大学）；IBM Research（IBM研究院）
Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform targeted misclassification of specific examples. In particular, backdoor attacks attempt to force a model to learn spurious relations between backdoor trigger patterns and false labels. In response to this threat, numerous defensive measures have been proposed; however, defenses against backdoor attacks focus on backdoor pattern detection, which may be unrelia…
Tongji University（同济大学）；Pennsylvania State University（宾夕法尼亚州立大学）
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive server-client communication gives room for backdoor attacks with aim to mislead the global model into a targeted misprediction when a specific trigger pattern is presented. In response to such backdoor threats on federated learning, various defense measures have been proposed. In this paper, we study whether the current defense mechanisms truly neutralize the backdoor threats from federated learning in a practical setting…
ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Miner School of Computer & Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校Miner计算机与信息科学学院）
Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers to backdoor poisoning attacks, specifically focusing on challenging "clean label" attacks where attackers do not control the sample labeling process. We propose the use of techniques from explainable machine learning to guide the selection of relevant features and values to create effective backdoor triggers in a model-agnostic fashion. Using multiple refer…
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）；Johns Hopkins University（约翰斯·霍普金斯大学）；Vietnam National University（越南国立大学）
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to raw training data, and (b) a new phenomenon we identify called backdoor leakage causes models trained continuously to eventually suffer from backdoors due to cumulative errors in defense mechanisms. We propose shadow learning, a framework for defending against backdoor attacks in the FL setting under long-range training. Shadow learning trains two models in…
Fuzhou University（福州大学）；East China Normal University（华东师范大学）
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose a novel backdoor defense method to mark and purify the infected neurons in the backdoored neural networks. Specifically, we first define a new metric, called benign salience. By combining the first-order gradient to retain the connections between neurons, benign salience can identify the infected neurons with higher accuracy than the commonly used metric in backdoor defense. Th…
Outlier detection and novelty detection are two important topics for anomaly detection. Suppose the majority of a dataset are drawn from a certain distribution, outlier detection and novelty detection both aim to detect data samples that do not fit the distribution. Outliers refer to data samples within this dataset, while novelties refer to new samples. In the meantime, backdoor poisoning attacks for machine learning models are achieved through injecting poisoning samples into the training dataset, which could be regarded as "outliers" that are intentionally added by attackers. Differential p…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word or phrase to an input. This paper considers the problem of diagnosing whether a model has been compromised and if so, identifying the backdoor trigger. We present the first robust defence mechanism that generalizes to several backdoor attacks against text classification models, without prior knowledge of the attack type, nor does our method require access to…
School of Computer Engineering and Science（计算机工程与科学学院）；Shanghai University（上海大学）
It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some special pattern called the backdoor trigger, the model with backdoor will carry out malicious task such as misclassification specified by adversaries. In text classification systems, backdoors inserted in the models can cause spam or malicious speech to escape detection. Previous work mainly focused on the defense of backdoor attacks in computer vision, little a…
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
Technical University of Munich（慕尼黑技术大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；School of Computation, Information and Technology（计算、信息与技术学院）
University of Science and Technology of China（中国科学技术大学）；Hong Kong University of Science and Technology（香港科技大学）
Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been made to detect and remove backdoors from backdoored DNNs, it is still not clear whether a backdoor-free clean model can be directly obtained from poisoned datasets. In this paper, we first construct a causal graph to model the generation process of poisoned data and find that the backdoor attack acts as the confounder, which brings spurious associations betwe…
