Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning scenario where data are partitioned by samples. The feature-partitioned learning can be another important scenario since in many real world applications, features are often distributed across different parties. Attacks and defenses in such scenario are especially challenging when the attackers have no labels and the defenders are not able to access the data and model parameters of other participants. In this paper, we show that even parties with no access to labels can successfully inject backdoor attacks, achieving high accuracy on both main and backdoor tasks. Next, we introduce several defense techniques, demonstrating that the backdoor can be successfully blocked by a combination of these techniques without hurting main task accuracy. To the best of our knowledge, this is the first systematical study to deal with backdoor attacks in the feature-partitioned collaborative learning framework.
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…
VinUniversity（文大大学）；Hanoi University of Science and Technology（河内科技大学）
Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it difficult for the orchestration server to validate the integrity of local model updates, making FL vulnerable to various threats, including backdoor attacks. Backdoor attacks involve the insertion of malicious functionality into a targeted model through poisoned updates from malicious clients. These attacks can cause the global model to misbehave on specific inputs while appeari…
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…
The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. However, FL is susceptible to backdoor attacks where a small fraction of malicious agents inject a targeted misclassification behavior in the global model by uploading polluted model updates to the server. In this work, we propose DifFense, an automated defense framework to protect an FL system from backdoor attacks by leveraging differential testing and two-step MAD outlier detection, without requiring any previous knowle…
Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but not the test inputs, while in a backdoor attack the attacker can also modify test inputs. Existing model-agnostic defense approaches either cannot handle backdoor attacks or do not provide effective certificates (i.e., a proof of a defense). We present BagFlip, a model-agnostic certified approach that can effectively defend against both trigger-less and bac…
FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
School of Cyber Science and Engineering, Wuhan University（武汉大学计算机科学与工程学院）；Department of Computer and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机与人工智能学院）；School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件工程学院）
State Key Laboratory of Integrated Services Networks (ISN)（综合业务网理论及关键技术国家重点实验室）；Shaanxi Key Laboratory of Network and System Security, Xidian University（西安电子科技大学陕西省网络与系统安全重点实验室）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）；Ant Group（蚂蚁集团）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）
Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the backdoor injected into the victim model through machine unlearning. Specifically, BAERASE mainly implements backdoor defense in two key steps. First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model. Here, the trigger pattern recovery problem is equivalent to the one of extracting an unknown noise distribution from…
Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
Dept. of Computer Science Faculty of Engineering University of Manchester Manchester, United Kingdom；Dept. of Computer Science Faculty of Engineering University of Manchester \& MBZUAI Abu Dhabi, United Arab Emirates；Dept. of Computer Science Faculty of Engineering University of Manchester \& KU Leuven Manchester, United Kingdom
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…
Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform backdoor attacks by poisoning the data (or gradients). Existing work on robust aggregation and certified FL robustness does not study how hardening benign clients can affect the global model (and the malicious clients). In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting. Moreo…
FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning
East China Normal University, Shanghai, China（华东师范大学）；Singapore Management University, Singapore（新加坡管理学院）；Nanyang Technological University, Singapore（南洋理工大学）；National University of Singapore, Singapore（国立新加坡大学）
Technical University of Darmstadt（达姆施塔特工业大学）；The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Federated learning (FL) allows participants to jointly train a machine learning model without sharing their private data with others. However, FL is vulnerable to poisoning attacks such as backdoor attacks. Consequently, a variety of defenses have recently been proposed, which have primarily utilized intermediary states of the global model (i.e., logits) or distance of the local models (i.e., L2-norm) from the global model to detect malicious backdoors. However, as these approaches directly operate on client updates, their effectiveness depends on factors such as clients' data distribution or …
Deep neural networks (DNNs) demonstrate superior performance in various fields, including scrutiny and security. However, recent studies have shown that DNNs are vulnerable to backdoor attacks. Several defenses were proposed in the past to defend DNNs against such backdoor attacks. In this work, we conduct a critical analysis and identify common pitfalls in these existing defenses, prepare a comprehensive database of backdoor attacks, conduct a side-by-side evaluation of existing defenses against this database. Finally, we layout some general guidelines to help researchers develop more robust …
Neural backdoor attack is emerging as a severe security threat to deep learning, while the capability of existing defense methods is limited, especially for complex backdoor triggers. In the work, we explore the space formed by the pixel values of all possible backdoor triggers. An original trigger used by an attacker to build the backdoored model represents only a point in the space. It then will be generalized into a distribution of valid triggers, all of which can influence the backdoored model. Thus, previous methods that model only one point of the trigger distribution is not sufficient. …
Deep Neural Networks are well known to be vulnerable to adversarial attacks and backdoor attacks, where minor modifications on the input are able to mislead the models to give wrong results. Although defenses against adversarial attacks have been widely studied, investigation on mitigating backdoor attacks is still at an early stage. It is unknown whether there are any connections and common characteristics between the defenses against these two attacks. We conduct comprehensive studies on the connections between adversarial examples and backdoor examples of Deep Neural Networks to seek to ans…
Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One important line of attacks against FL is the backdoor attacks. In a backdoor attack, an adversary tries to embed a backdoor functionality to the model during training that can later be activated to cause a desired misclassification. To prevent backdoor attacks, we propose a lightweight defense that requires…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the attacker defined trigger. This threat could happen when the training process is not fully controlled, such as training on third-party data-sets or adopting third-party models. There has been a lot of research and different methods to defend such type of backdoor attacks, one being robustness-aware perturbation-based defense method. This method mainly exploits…
Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although there exist various defense methods that can effectively erase backdoors from DNNs, they greatly suffer from both high Attack Success Rate (ASR) and a non-negligible loss in Benign Accuracy (BA). Inspired by the observation that a backdoored DNN tends to form a new cluster in its feature spaces for poisoned data, in this paper we propose a novel two-stage b…
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…
Pennsylvania State University（宾夕法尼亚州立大学）；Zhejiang University（浙江大学）；Hong Kong Polytechnic University（香港理工大学）
Neural backdoors represent one primary threat to the security of deep learning systems. The intensive research has produced a plethora of backdoor attacks/defenses, resulting in a constant arms race. However, due to the lack of evaluation benchmarks, many critical questions remain under-explored: (i) what are the strengths and limitations of different attacks/defenses? (ii) what are the best practices to operate them? and (iii) how can the existing attacks/defenses be further improved? To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural b…
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of a backdoored network embed new features to detect the presence of a trigger and the subsequent classification layers learn to mispredict when triggers are detected. Therefore, to detect backdoors, the proposed defense uses two synergistic anomaly detectors trained on clean validation data: the first is a novelty detector that checks for anomalous features, …
Reconstructive Neuron Pruning for Backdoor Defense
Xidian University（西安电子科技大学）；Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Copenhagen（哥本哈根大学）；Sony AI（索尼人工智能）；University of Illinois at Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hidden triggers. During deployment, the adversary can modify observed states in a particular way to trigger unexpected actions and harm the agent. We assume the agent does not have the resources to re-train a good policy. Instead, our defense mechanism sanitizes the backdoor policy by projecting observed states to a 'safe subspace', estimated from a …
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…
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学跨学科安全、可靠性与信任中心（SnT））；Singapore University of Technology and Design（新加坡科技设计大学）
The introduction of robust optimisation has pushed the state-of-the-art in defending against adversarial attacks. Notably, the state-of-the-art projected gradient descent (PGD)-based training method has been shown to be universally and reliably effective in defending against adversarial inputs. This robustness approach uses PGD as a reliable and universal "first-order adversary". However, the behaviour of such optimisation has not been studied in the light of a fundamentally different class of attacks called backdoors. In this paper, we study how to inject and defend against backdoor attacks f…
Recent exploration of the multi-agent backdoor attack demonstrated the backfiring effect, a natural defense against backdoor attacks where backdoored inputs are randomly classified. This yields a side-effect of low accuracy w.r.t. clean labels, which motivates this paper's work on the construction of multi-agent backdoor defenses that maximize accuracy w.r.t. clean labels and minimize that of poison labels. Founded upon agent dynamics and low-loss subspace construction, we contribute three defenses that yield improved multi-agent backdoor robustness.
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…
Backdoor (Trojan) attacks are emerging threats against deep neural networks (DNN). A DNN being attacked will predict to an attacker-desired target class whenever a test sample from any source class is embedded with a backdoor pattern; while correctly classifying clean (attack-free) test samples. Existing backdoor defenses have shown success in detecting whether a DNN is attacked and in reverse-engineering the backdoor pattern in a "post-training" regime: the defender has access to the DNN to be inspected and a small, clean dataset collected independently, but has no access to the (possibly poi…
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior of the trained model when triggered by an attacker-specified watermark. Such a compromised model will be deployed unnoticed as the model is accurate otherwise. There have been promising attempts to use the intermediate representations of such a model to separate corrupted examples from clean ones. However, these defenses work only when a certain spectral sign…
Pennsylvania State University（宾夕法尼亚州立大学）；Anomalee Inc.（Anomalee 公司）；Imperial College（帝国理工学院）
We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples are surrounded by correctly labeled ones. We demonstrate how such localization is necessary for attack success. We also study the performance of a backdoor defense using gradient-based discovery of local error maximizers. Local error maximizers which are associated with significant (interpolation) error, and are proximal to many training samples, are suspicious. This method is also used to accurately train for deep r…
New York University（纽约大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time adversarial attacks. Recent work has demonstrated that a small fraction of malicious physical designers can stealthily "backdoor" a DL-based hotspot detector during its training phase such that it accurately classifies regular layout clips but predicts hotspots containing a specially crafted trigger shape as non-hotspots. We propose a novel training data au…
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…
Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we propose a novel model backdoor forensics technique. Given a few attack samples such as inputs with backdoor triggers, which may represent different types of backdoors, our technique automatically decomposes them to clean inputs and the corresponding triggers. It then clusters the triggers based on their properties to allow automatic attack categorization…
In this work, we propose the first backdoor attack to graph neural networks (GNN). Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification. In our backdoor attack, a GNN classifier predicts an attacker-chosen target label for a testing graph once a predefined subgraph is injected to the testing graph. Our empirical results on three real-world graph datasets show that our backdoor attacks are effective with a small impact on a GNN's prediction accuracy for clean testing graphs. Moreover, we generalize a randomized smoothing based certified defense to def…
