A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a specific label. Prior research on this problem assumes the dominance of the trigger in an image's representation, which causes any image with the trigger to be recognized as a member in the target class. Such a trigger also exhibits unique features in the representation space and can therefore be easily separated from legitimate images. Our research, however, shows that simple target contamination can cause the representation of an attack image to be less distinguishable from that of legitimate ones, thereby evading existing defenses against the backdoor infection.
In our research, we show that such a contamination attack actually subtly changes the representation distribution for the target class, which can be captured by a statistic analysis. More specifically, we leverage an EM algorithm to decompose an image into its identity part (e.g., person, traffic sign) and variation part within a class (e.g., lighting, poses). Then we analyze the distribution in each class, identifying those more likely to be characterized by a mixture model resulted from adding attack samples to the legitimate image pool. Our research shows that this new technique effectively detects data contamination attacks, including the new one we propose, and is also robust against the evasion attempts made by a knowledgeable adversary.
Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if hidden backdoors are activated by the attacker-defined trigger. Existing backdoor attacks usually adopt the setting that triggers are sample-agnostic, $i.e.,$ different poisoned samples contain the same trigger, resulting in that the attacks could be easily mitigated by current backdoor defenses. In this work, we expl…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；University of Oxford（牛津大学）
In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. Building on these findings, we propose FREAK, a frequency-based poisoned sample detection algorithm that is simple yet effective. Our experimental results demonstrate the efficacy of FREAK not only against frequency backdoor attacks but also against some spatial attacks. Our work is just the first step in leveraging these insights. We believe that o…
We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). Most state-of-the-art defenses rely on the statistical sanitization of the "inputs" or "latent DNN representations" to capture trojan behaviour. In this paper, we first challenge the robustness of such recently reported defenses by introducing a novel variant of targeted backdoor attack, called "low-confidence backdoor attack". We also propose a novel defense technique, called "HaS-Nets". "Low-confidence backdoor attack" exploits the confidence labels ass…
Peking University（北京大学）；Tsinghua University（清华大学）；University of Tokyo（东京大学）
As deep neural networks (DNNs) are growing larger, their requirements for computational resources become huge, which makes outsourcing training more popular. Training in a third-party platform, however, may introduce potential risks that a malicious trainer will return backdoored DNNs, which behave normally on clean samples but output targeted misclassifications whenever a trigger appears at the test time. Without any knowledge of the trigger, it is difficult to distinguish or recover benign DNNs from backdoored ones. In this paper, we first identify an unexpected sensitivity of backdoored DNN…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Third-party resources ($e.g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat. In general, backdoor attackers intend to implant hidden backdoor in DNNs, so that the attacked DNNs behave normally on benign samples whereas their predictions will be maliciously changed to a pre-defined target label if hidden backdoors are activated by attacker-specified trigger patterns. To facilitate the research and development of more secure training schemes and defenses, we design an …
One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backdoor attacks on deep neural networks (DNNs) in the production stage (or training stage) and corresponding defenses are extensively explored in recent years. Ironically, backdoor attacks in the deployment stage, which can often happen in unprofessional users' devices and are thus arguably far more threatening in real-world scenarios, draw much less attention of the community. We attribute this imbalance of vigilance to…
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of DNNs under the real-world machine learning as a service (MLaaS) setting, where the deployed model is fully black-box while the users can only query and obtain its predictions. Currently, there are many existing defenses to reduce backdoor threats. However, almost all of them cannot be adopted in MLaaS scenarios since they require getting access to or even modif…
Backdoor Attacks on Transformers for Tabular Data: An Empirical Study
Radboud University（拉德堡德大学）；Delft University of Technology（代尔夫特理工大学）；Ikerlan Technology Research Centre（Ikerlan技术研究中心）；University of Zagreb Faculty of Electrical Engineering and Computing（Zagreb大学电子工程与计算学院）；University of Bergen（卑尔根大学）
Research Center for Computer Network (Shenzhen) Ministry of Education（教育部计算机网络（深圳）研究中心）
Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process. One recent research revealed that most of the existing attacks failed in the real physical world since the trigger contained in the digitized test samples may be different from that of the one used for training. Accordingly, users can adopt spatial transformations as the image pre-processing to deactivate hidden backdoors. In…
Shanghai Jiao Tong University（上海交通大学）；Rutgers University（罗格斯大学）；The University of Adelaide（阿德莱德大学）；The University of New South Wales（新南威尔士大学）；Data61 CSIRO（联邦科学与工业研究组织Data61研究所）
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its input contains a malicious trigger. The trigger can take a plethora of forms, including a special object present in the image (e.g., a yellow pad), a shape filled with custom textures (e.g., logos with particular colors) or even image-wide stylizations with special filters (e.g., images altered by Nashville or Gotham filters). These filters can be applied to …
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…
Zhejiang University（浙江大学）；Tencent Zhuque Lab（腾讯朱雀实验室）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tencent（腾讯）
We study the realistic potential of conducting backdoor attack against deep neural networks (DNNs) during deployment stage. Specifically, our goal is to design a deployment-stage backdoor attack algorithm that is both threatening and realistically implementable. To this end, we propose Subnet Replacement Attack (SRA), which is capable of embedding backdoor into DNNs by directly modifying a limited number of model parameters. Considering the realistic practicability, we abandon the strong white-box assumption widely adopted in existing studies, instead, our algorithm works in a gray-box setting…
For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain, inherent structures of different image formats are similar. Hence, backdoor attack designed for one image format will suite for others. However, when it comes to 3D world, there is a huge disparity among different 3D data structures. As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene. Therefore, this paper designs a uniform backdoor …
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）
Recent studies have shown that Deep Neural Networks (DNNs) are vulnerable to the backdoor attacks, which leads to malicious behaviors of DNNs when specific triggers are attached to the input images. It was further demonstrated that the infected DNNs possess a collection of channels, which are more sensitive to the backdoor triggers compared with normal channels. Pruning these channels was then shown to be effective in mitigating the backdoor behaviors. To locate those channels, it is natural to consider their Lipschitzness, which measures their sensitivity against worst-case perturbations on t…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）
Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process. Specifically, the adversaries intend to embed hidden backdoors in DNNs so that malicious model predictions can be activated through pre-defined trigger patterns. In this paper, we explore the backdoor mechanism from the angle of the model structure. We select the skip connection for discussions, inspired by the understanding that it helps the learning of model `shortcuts' where backdoor triggers are usually easier to be learned. Specifically, we demonstrate that the…
The backdoor or Trojan attack is a severe threat to deep neural networks (DNNs). Researchers find that DNNs trained on benign data and settings can also learn backdoor behaviors, which is known as the natural backdoor. Existing works on anti-backdoor learning are based on weak observations that the backdoor and benign behaviors can differentiate during training. An adaptive attack with slow poisoning can bypass such defenses. Moreover, these methods cannot defend natural backdoors. We found the fundamental differences between backdoor-related neurons and benign neurons: backdoor-related neuron…
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…
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）
Peking University（北京大学）；Sony AI（索尼人工智能）；Fudan University（复旦大学）；Washington University in St. Louis（圣路易斯华盛顿大学）
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned samples. Although the clean weights of PLMs are readily available, existing methods have ignored this information in defending NLP models against backdoor attacks. In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models. Specifically, we leverage the clean pre-trained weights via t…
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…
Universitat Rovira i Virgili（罗维拉-威尔吉利大学）；Tsinghua University（清华大学）
Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models. Unfortunately, doing so facilitates a new training-time attack (i.e., backdoor attack) against DNNs. This attack aims to induce misclassification of input samples containing adversary-specified trigger patterns. In this paper, we first conduct a layer-wise feature analysis of poisoned and benign samples from the target class. We find out that the feature differe…
Shanghai Jiao Tong University（上海交通大学）；The University of Adelaide（阿德莱德大学）；The University of New South Wales（新南威尔士大学）；Data61 CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Shanghai Institute for Advanced Communication and Data Science（上海先进通信与数据科学研究院）；Shanghai University（上海大学）
Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this paper, we create covert and scattered triggers for backdoor attacks, invisible backdoors, where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steg…
Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against backdoor attacks but they are soon broken by strong adaptive backdoor attacks. To prevent such cat-and-mouse game, we take the first step towards certified defenses against backdoor attacks. Specifically, in this work, we study the feasibility and effectiveness of certifying robustness against backdoor attacks using a recent technique called randomized smooth…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific inputs, which cause the neural network to produce incorrect outputs. The state-of-the-art backdoor attack work is implemented by data poisoning, i.e., the attacker injects poisoned samples into the dataset, and the models trained with that dataset are infected with the backdoor. However, most of the triggers used in the current study are fixed patterns patched…
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Deakin University（德肯大学）；Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist大学）；University of New South Wales（新南威尔士大学）；Griffith University（格里菲斯大学）
Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are rarely static but evolve continuously to address distribution drifts in the underlying data. This paper explores the behavior of backdoor attacks in time-varying models, whose model weights are continually updated via fine-tuning to adapt to data drifts. Our theoretical analysis shows how fine-tuning with fresh data progressively "erases" the injected backdo…
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible. To solve these problems, we propose a two-phase and image-specific triggers generation method to enhance clean-label …
Tsinghua University（清华大学）；The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in the presence of a predefined trigger pattern, which can be easily realized via poisoning a small amount of data. In general, adversarial training is believed to defend against backdoor attacks since it helps models to keep their prediction unchanged even if we perturb the input image (as long as within a feasible range). Unfortunately, few previous studies s…
Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific inputs. In practice, however, these attacks are difficult to perform and highly constrained by sharing of models through transfer learning. Adversaries have a small window during which they must compromise the student model before it is deployed. In this paper, we describe a significantly more powerful variant of the backdoor attack, latent backdoors, where hidden rules can be embedded in a single "Teacher" model, a…
Pennsylvania State University（宾夕法尼亚州立大学）；Zhejiang University（浙江大学）
One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally otherwise. Despite the plethora of prior work on DNNs for continuous data (e.g., images), the vulnerability of graph neural networks (GNNs) for discrete-structured data (e.g., graphs) is largely unexplored, which is highly concerning given their increasing use in security-sensitive domains. To bridge this gap, we present GTA, the first backdoor attack on GNNs. Compared with prio…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；PCL Research Center of Networks and Communications, Peng Cheng Laboratory（鹏城实验室网络与通信研究中心）
Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be changed to a particular target label if hidden backdoors are activated. So far, backdoor research has mostly been conducted towards classification tasks. In this paper, we reveal that this threat could also happen in semantic segmentation, which may further endanger many mission-critical applications ($e.g.$, autonomous driving). Except for extending the existin…
