Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the attacks. In this paper, we propose a novel strategy for hiding backdoor and poisoning attacks. Our approach builds on a recent class of attacks against image scaling. These attacks enable manipulating images such that they change their content when scaled to a specific resolution. By combining poisoning and image-scaling attacks, we can conceal the trigger of backdoors as well as hide the overlays of clean-label poisoning. Furthermore, we consider the detection of image-scaling attacks and derive an adaptive attack. In an empirical evaluation, we demonstrate the effectiveness of our strategy. First, we show that backdoors and poisoning work equally well when combined with image-scaling attacks. Second, we demonstrate that current detection defenses against image-scaling attacks are insufficient to uncover our manipulations. Overall, our work provides a novel means for hiding traces of manipulations, being applicable to different poisoning approaches.
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…
Provable Responsible AI and Data Analytics (PRADA) Lab（可证负责任人工智能与数据分析实验室）；King Abdullah University of Science and Technology（卡塔尔国王科技大学）；University of Electronic Science and Technology of China（电子科技大学）；Stony Brook University（石溪大学）；University of Virginia（弗吉尼亚大学）；University of Copenhagen（哥本哈根大学）
KASTEL Security Research Labs（KASTEL安全研究实验室）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In this paper, we demonstrate blinding attacks that can fully disguise an ongoing attack against the machine learning model. Similar to neural backdoors, we modify the model's prediction upon trigger presence but simultaneously also fool the provided explanation. This enables an adversary to hide the presence of the trigger or point the explanation to entirely d…
Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced training introduces the risk that a malicious trainer will return a backdoored DNN that behaves normally on most inputs but causes targeted misclassifications or degrades the accuracy of the network when a trigger known only to the attacker is present. In this paper, we provide the first effective defenses against backdoor attacks on DNNs. We implement three…
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）
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）
Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithm…
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…
BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
Hong Kong University of Science and Technology（香港科技大学）；Carnegie Mellon University（卡内基梅隆大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Tsinghua University（清华大学）；China Mobile Communications Group Co., Ltd.（中国移动通信集团有限公司）；Bosch（博世）；RealAI（瑞莱智慧）
Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have to inject the poisoned data in advance before training, and the order of feeding these poisoned batches into the model is stochastic. In contrast, practical systems are more usually trained/fine-tuned on sequentially captured real-time data, in which case poisoning adversaries could dynamically poison each data batch according to the current model state. In…
Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to identify such attacks. In this work, we take a different approach to preventing data poisoning attacks which relies on cryptographically-based authentication and provenance to ensure the integrity of the data used to train a machine learning model. The same approach is also used to prevent software poisoning and model poisoning attacks. A software poisoning…
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…
Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a data poisoning attack to contrastive learning. In particular, an attacker injects carefully crafted poisoning inputs into the unlabeled pre-training data, such that the downstream classifiers built based on the poisoned encoder for multiple target downstream tasks simultaneously classify attacker-chosen, arbitrary clean inputs as attacker-chosen, arbitrary …
With the extensive use of AI in various fields, the issue of AI security has become more significant. The AI data poisoning attacks will be the most threatening approach against AI security after the adversarial examples. As the continuous updating of AI applications online, the data pollution models can be uploaded by attackers to achieve a certain malicious purpose. Recently, the research on AI data poisoning attacks is mostly out of practice and use self-built experimental environments so that it cannot be as close to reality as adversarial example attacks. This article's first contribution…
University of South Florida（南佛罗里达大学）；Fordham University（福特汉姆大学）
Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considera…
Microsoft Research（微软研究院）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Rutgers University（罗格斯大学）
Machine learning (ML) has made tremendous progress during the past decade and is being adopted in various critical real-world applications. However, recent research has shown that ML models are vulnerable to multiple security and privacy attacks. In particular, backdoor attacks against ML models have recently raised a lot of awareness. A successful backdoor attack can cause severe consequences, such as allowing an adversary to bypass critical authentication systems. Current backdooring techniques rely on adding static triggers (with fixed patterns and locations) on ML model inputs which are pr…
Federated learning (FL) has become an emerging machine learning technique lately due to its efficacy in safeguarding the client's confidential information. Nevertheless, despite the inherent and additional privacy-preserving mechanisms (e.g., differential privacy, secure multi-party computation, etc.), the FL models are still vulnerable to various privacy-violating and security-compromising attacks (e.g., data or model poisoning) due to their numerous attack vectors which in turn, make the models either ineffective or sub-optimal. Existing adversarial models focusing on untargeted model poison…
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…
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…
Federated learning has become prevalent in medical diagnosis due to its effectiveness in training a federated model among multiple health institutions (i.e. Data Islands (DIs)). However, increasingly massive DI-level poisoning attacks have shed light on a vulnerability in federated learning, which inject poisoned data into certain DIs to corrupt the availability of the federated model. Previous works on federated learning have been inadequate in ensuring the privacy of DIs and the availability of the final federated model. In this paper, we design a secure federated learning mechanism with mul…
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…
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…
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 are resistant to data poisoning attacks when the adversary is only able to poison a small number of items. However, this protection degrades as the adversary poisons more data. To illustrate, we design attack algorithms targeting objective and output perturbation learners, two standard approaches to differentially-private machine learning. Experiments show …
University of Virginia（弗吉尼亚大学）；Princeton University（普林斯顿大学）
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 against convex machine learning models and propose an efficient poisoning attack designed to induce a specified model. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to {\it any} attainable target classifier. The distance from the induced classifier to the target classifier is inversely proportional to the square root …
The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but the data privacy and security exposure in IoT devices, especially in the automatic driving system. Federated learning (FL) is a paradigm that addresses data privacy, security, access rights, and access to heterogeneous message issues by integrating a global model based on distributed nodes. However, data poisoning attacks on FL can undermine the benefits, destroying the global model's availability and disrupting model training. To avoid the above issues, we build up a hierarchical defens…
Federated learning (FL) enables the training of models among distributed clients without compromising the privacy of training datasets, while the invisibility of clients datasets and the training process poses a variety of security threats. This survey provides the taxonomy of poisoning attacks and experimental evaluation to discuss the need for robust FL.
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points. Even if the capabilities of the attacker are constrained, these attacks have been shown to be effective to signif…
Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique that induces catastrophic forgetting on an online model. We apply the attack in the context of Test-Time Training, a modern online learning framework aimed for generalization under distribution shifts. We present the theoretical rationale and empirically compare it against other sample sequences that naturally induce forgetting. Our results demonstrate that using lethean attacks, …
Although local differential privacy (LDP) protects individual users' data from inference by an untrusted data curator, recent studies show that an attacker can launch a data poisoning attack from the user side to inject carefully-crafted bogus data into the LDP protocols in order to maximally skew the final estimate by the data curator. In this work, we further advance this knowledge by proposing a new fine-grained attack, which allows the attacker to fine-tune and simultaneously manipulate mean and variance estimations that are popular analytical tasks for many real-world applications. To acc…
Princeton University（普林斯顿大学）；University of Chicago（芝加哥大学）；IBM
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce \algoname{}, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks…
Local Differential Privacy (LDP) protocols enable an untrusted server to perform privacy-preserving, federated data analytics. Various LDP protocols have been developed for different types of data such as categorical data, numerical data, and key-value data. Due to their distributed settings, LDP protocols are fundamentally vulnerable to poisoning attacks, in which fake users manipulate the server's analytics results via sending carefully crafted data to the server. However, existing poisoning attacks focused on LDP protocols for simple data types such as categorical and numerical data, leavin…
