Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack that has attracted a great deal of attention recently is the backdoor attack. Specifically, the adversary poisons the target model's training set to mislead any input with an added secret trigger to a target class.
Previous backdoor attacks predominantly focus on computer vision (CV) applications, such as image classification. In this paper, we perform a systematic investigation of backdoor attack on NLP models, and propose BadNL, a general NLP backdoor attack framework including novel attack methods. Specifically, we propose three methods to construct triggers, namely BadChar, BadWord, and BadSentence, including basic and semantic-preserving variants. Our attacks achieve an almost perfect attack success rate with a negligible effect on the original model's utility. For instance, using the BadChar, our backdoor attack achieves a 98.9% attack success rate with yielding a utility improvement of 1.5% on the SST-5 dataset when only poisoning 3% of the original set. Moreover, we conduct a user study to prove that our triggers can well preserve the semantics from humans perspective.
Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly validated in the CV field. In this paper, we find that NLP backdoors are hard to defend against than CV, and we provide a theoretical analysis that the malicious update detection error probabilities are determined by the relative backdoor strengths. NLP attacks tend to have small relative backdoor strengths, which may result in the failure of robust federated aggregation methods for …
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…
Although backdoor learning is an active research topic in the NLP domain, the literature lacks studies that systematically categorize and summarize backdoor attacks and defenses. To bridge the gap, we present a comprehensive and unifying study of backdoor learning for NLP by summarizing the literature in a systematic manner. We first present and motivate the importance of backdoor learning for building robust NLP systems. Next, we provide a thorough account of backdoor attack techniques, their applications, defenses against backdoor attacks, and various mitigation techniques to remove backdoor…
As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In particular, Deep Neural Networks (DNN) have been shown to be vulnerable to backdoor attacks whereby adversaries have access to the training data and the opportunity to manipulate such data by inserting carefully developed samples into the training dataset. Although the NLP community has produced several studies on generating backdoor attacks proving the vulnerable st…
Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the poisoned models with malicious intentions are much more dangerous in real life. However, most existing works currently focus on the adversarial attacks on NLP models instead of positioning attacks, also named \textit{backdoor attacks}. In this paper, we first propose the \textit{natural backdoor attacks} on NLP models. Moreover, we exploit the various attack …
SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
Department of Information and Communication Engineering, Major in Information Security, Chosun University（信息与通信工程系，信息安全专业，全州大学）；AI Data Security Research Section, Electronics and Telecommunications Research Institute（人工智能数据安全研究部，电子电信研究院）；Department of Convergence Science, Kongju National University（融合科学系， Kongju国立大学）
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…
Zhejiang University（浙江大学）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；Wuhan University（武汉大学）；Huawei International, Singapore（华为国际）；Pennsylvania State University（宾夕法尼亚州立大学）
Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most existing backdoor attacks in NLP are conducted in the fine-tuning phase by introducing malicious triggers in the targeted class, thus relying greatly on the prior knowledge of the fine-tuning task. In this paper, we propose a new approach to map the inputs containing triggers directly to a predefined output representation of the pre-trained NLP models, e.g.,…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；McGill University（麦吉尔大学）
Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated, presenting serious security threats to real-world applications. Since existing textual backdoor attacks pay little attention to the invisibility of backdoors, they can be easily detected and blocked. In this work, we present invisible backdoors that are activated by a learnable combination of word substitution. We show that NLP models can be inje…
Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；State Key Laboratory of Cyberspace Security Defense（网络空间安全防御国家重点实验室）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Chongqing University（重庆大学）；Peng Cheng Laboratory（鹏城实验室）；Peking University（北京大学）
Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This strategy comes with a severe flaw of being easily detected from both the trigger and the label perspectives: the trigger injected, which is usually a rare word, leads to an abnormal natural language expression, and thus can be easily detected by a defense model; the changed target label leads the example to be mistakenly labeled and thus can be easily detected by…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources being limited. In such a situation, training data and models are exposed to the public. As a result, attackers can manipulate the training process to inject some triggers into the model, which is called backdoor attack. Backdoor attack is quite stealthy and difficult to be detected because it has little inferior influence on the model's performance for the cle…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；Huazhong University of Science and Technology（华中科技大学）；Beihang University（北京航空航天大学）
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to most NLP tasks, and thus suitable for adversarial and backdoor attacks. In this paper, we make the first attempt to conduct adversarial and backdoor attacks based on text style transfer, which is aimed at altering the style of a sentence while preserving its meaning. We design an adversarial attack method and a backdoor attack method, and conduct extensive exp…
Shanghai Jiao Tong University（上海交通大学）；University of New South Wales（新南威尔士大学）；CSIRO-Data61（澳大利亚联邦科学与工业研究组织数据61）；The University of Adelaide（阿德莱德大学）
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replaceme…
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threatening backdoor attack is the stealthy backdoor, which defines the triggers as text style or syntactic. Although they have achieved an incredible high attack success rate (ASR), we find that the principal factor contributing to their ASR is not the `backdoor trigger' paradigm. Thus the capacity of these stealthy backdoor attacks is overestimated when categorized as backdoor attac…
The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses a serious threat to their security. Previous research on backdoor attacks has been limited to uni-modal tasks or single tasks across modalities, making it inapplicable to unified foundation models. In this paper, we make proof-of-concept level research on the backdoor attack for pre-trained unified foundation models. Through preliminary experiments on NLP a…
Monash University（莫纳什大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61研究所）；The University of Melbourne（墨尔本大学）
Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for steering them to undesirable behaviors. Most existing backdoor attacks, such as data poisoning, require further (re)training or fine-tuning language models to learn the intended backdoor patterns. The additional training process however diminishes the stealthiness of the attacks, as training a language model usually requires long optimization time, a massive am…
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly inject a small number of poisoned samples into the training dataset with the labels changed to the target one. Such mislabeled samples would raise suspicion upon human inspection, potentially revealing the attack. To improve the stealthiness of textual backdoor attacks, we propose the first clean-label framework Kallima for synthesizing mimesis-style backdoor sa…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Boston University（波士顿大学）
Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds triggers in the model and controls the model behavior when the triggers are presented, little is known whether such an attack is still valid on the transformer models and if so, whether it can be done in a more cost-efficient manner. In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inhe…
Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor attacks are one such attack where a neural network is made to perform in a certain way on specific samples containing some triggers while achieving normal results on other samples. In this work, we present a few defense strategies that can be useful to counter against such an attack. We show that our defense methodologies significantly decrease the performa…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Beihang University（北京航空航天大学）；Huazhong University of Science and Technology（华中科技大学）
Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned triggers but behave properly on normal inputs during inference. As a sort of emergent attack, backdoor attacks in natural language processing (NLP) are investigated insufficiently. As far as we know, almost all existing textual backdoor attack methods insert additional contents into normal samples as triggers, which causes the trigger-embedded samples to be de…
Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the adversary injects a backdoor into the model during the training phase, so that input samples with backdoor triggers are classified as the target class. Some attacks have achieved high attack success rates on the pre-trained language models (LMs), but there have yet to be effective defense methods. In this work, we propose a defense method based on deep model …
Tsinghua University（清华大学）；Huazhong University of Science and Technology（华中科技大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been proposed, it is of great significance to perform rigorous evaluations. However, we highlight two issues in previous backdoor learning evaluations: (1) The differences between real-world scenarios (e.g. releasing poisoned datasets or models) are neglected, and we argue that each scenario has its own constraints and concerns, thus requires specific evaluation pro…
Dependable Artificial Intelligence with Reliability and Security (DAIReS): A Unified Syndrome Decoding Approach for Hallucination and Backdoor Trigger Detection
National Institute of Advanced Studies, Indian Institute of Science Campus（印度科学学院校园高等研究院）
Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
The Hong Kong University of Science and Technology（香港科技大学）；National University of Singapore（新加坡国立大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The increasing deployment of DNNs in critical systems and the surge of outsourcing DNN training (which makes Trojan attack easier) makes the detection of Trojan attacks necessary. While Neural Trojan detection has been studied in the image domain, there is a lack of solutions in the NLP domain. In this paper, we propose a model-level Trojan detection framework by analyzi…
A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Nanyang Technological University（南洋理工大学）；Beijing Institute of Technology（北京理工大学）；University of St Andrews（圣安德鲁斯大学）；Zhejiang University（浙江大学）；Shanghai AI Lab（上海人工智能实验室）
Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way by aggregating model updates. However, for many natural language processing (NLP) tasks that utilize pre-trained language models (PLMs) with large numbers of parameters, there are considerable communication costs associated with FL. Recently, prompt tuning, which tunes some soft prompts without modifying PLMs, has achieved excellent performance as a new learning paradigm. Therefore we want to combine the two methods and explore the effect of prompt tuning under FL. In this paper, we prop…
