Backdoor Attacks

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data. In this paper, we introduce a more realistic attack scenario where victims collect data from multiple sources, and attackers cannot access the complete training data. We refer to this scenario as $\textbf{data-constrained backdoor attacks}$. In such cases, previous attack methods suffer from severe efficiency degradation due to the $\textbf{entanglement}$ between benign and poisoning features during the backdoor injection process. To tackle this problem, we introduce three CLIP-based technologies from two distinct streams: $\textit{Clean Feature Suppression}$ and $\textit{Poisoning Feature Augmentation}$. The results demonstrate remarkable improvements, with some settings achieving over $\textbf{100}$% improvement compared to existing attacks in data-constrained scenarios.

Vertical Federated Learning (VFL) has emerged as a collaborative training paradigm that allows participants with different features of the same group of users to accomplish cooperative training without exposing their raw data or model parameters. VFL has gained significant attention for its research potential and real-world applications in recent years, but still faces substantial challenges, such as in defending various kinds of data inference and backdoor attacks. Moreover, most of existing VFL projects are industry-facing and not easily used for keeping track of the current research progress. To address this need, we present an extensible and lightweight VFL framework VFLAIR (available at https://github.com/FLAIR-THU/VFLAIR), which supports VFL training with a variety of models, datasets and protocols, along with standardized modules for comprehensive evaluations of attacks and defense strategies. We also benchmark $11$ attacks and $8$ defenses performance under different communication and model partition settings and draw concrete insights and recommendations on the choice of defense strategies for different practical VFL deployment scenarios.

Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous methods, starting from reconstructing a single data point and then relaxing the single-image limit to batch level, are only tested under hard label constraints. Even for single-image reconstruction, we still lack an analysis-based algorithm to recover augmented soft labels. In this work, we change the focus from enlarging batchsize to investigating the hard label constraints, considering a more realistic circumstance where label smoothing and mixup techniques are used in the training process. In particular, we are the first to initiate a novel algorithm to simultaneously recover the ground-truth augmented label and the input feature of the last fully-connected layer from single-input gradients, and provide a necessary condition for any analytical-based label recovery methods. Extensive experiments testify to the label recovery accuracy, as well as the benefits to the following image reconstruction. We believe soft labels in classification tasks are worth further attention in gradient inversion attacks.

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that operate independently of how the model was generated. The proposed defense is built upon a novel reverse engineering approach that can directly extract **backdoor functionality** of a given backdoored model to a *backdoor expert* model. The approach is straightforward --- finetuning the backdoored model over a small set of intentionally mislabeled clean samples, such that it unlearns the normal functionality while still preserving the backdoor functionality, and thus resulting in a model~(dubbed a backdoor expert model) that can only recognize backdoor inputs. Based on the extracted backdoor expert model, we show the feasibility of devising highly accurate backdoor input detectors that filter out the backdoor inputs during model inference. Further augmented by an ensemble strategy with a finetuned auxiliary model, our defense, **BaDExpert** (**Ba**ckdoor Input **D**etection with Backdoor **Expert**), effectively mitigates 17 SOTA backdoor attacks while minimally impacting clean utility. The effectiveness of BaDExpert has been verified on multiple datasets (CIFAR10, GTSRB and ImageNet) across various model architectures (ResNet, VGG, MobileNetV2 and Vision Transformer). Our code is integrated into our research toolbox: [https://github.com/vtu81/backdoor-toolbox](https://github.com/vtu81/backdoor-toolbox).

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack target class, thus fooling the downstream predictor to misclassify it as the target. Existing attacks usually adopt a fixed trigger pattern and poison the training set with trigger-injected data, hoping for the feature extractor to learn the association between trigger and target class. However, we find that such fixed trigger design fails to effectively associate trigger-injected data with target class in the embedding space due to special CL mechanisms, leading to a limited attack success rate (ASR). This phenomenon motivates us to find a better backdoor trigger design tailored for CL framework. In this paper, we propose a bi-level optimization approach to achieve this goal, where the inner optimization simulates the CL dynamics of a surrogate victim, and the outer optimization enforces the backdoor trigger to stay close to the target throughout the surrogate CL procedure. Extensive experiments show that our attack can achieve a higher attack success rate (e.g., 99\% ASR on ImageNet-100) with a very low poisoning rate (1\%). Besides, our attack can effectively evade existing state-of-the-art defenses.

Convolutional neural network (CNN) is easily affected by backdoor injections, whose models perform normally on clean samples but produce specific outputs on poisoned ones. Most of the existing studies have focused on the effect of trigger feature changes of poisoned samples on model generalization in spatial domain. We focus on the mechanism of CNN memorize poisoned samples in frequency domain, and find that CNN generate generalization to poisoned samples by memorizing the frequency domain distribution of trigger changes. We also explore the influence of trigger perturbations in different frequency domain components on the generalization of poisoned models from visible and invisible backdoor attacks, and prove that high-frequency components are more susceptible to perturbations than low-frequency components. Based on the above fundings, we propose a universal invisible strategy for visible triggers, which can achieve trigger invisibility while maintaining raw attack performance. We also design a novel frequency domain backdoor attack method based on low-frequency semantic information, which can achieve 100\% attack accuracy on multiple models and multiple datasets, and can bypass multiple defenses.

Adversarial robustness is an important standard for measuring the quality of learned models, and adversarial training is an effective strategy for improving the adversarial robustness of models. In this paper, we disclose that adversarially trained models are vulnerable to two-faced attacks, where slight perturbations in input features are crafted to make the model exhibit a false sense of robustness in the verification phase. Such a threat is significantly important as it can mislead our evaluation of the adversarial robustness of models, which could cause unpredictable security issues when deploying substandard models in reality. More seriously, this threat seems to be pervasive and tricky: we find that many types of models suffer from this threat, and models with higher adversarial robustness tend to be more vulnerable. Furthermore, we provide the first attempt to formulate this threat, disclose its relationships with adversarial risk, and try to circumvent it via a simple countermeasure. These findings serve as a crucial reminder for practitioners to exercise caution in the verification phase, urging them to refrain from blindly trusting the exhibited adversarial robustness of models.

Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side detectability of MS attacks were raised, questioning their practicality. In this work, for the first time, we thoroughly study client-side detectability. We first demonstrate that all prior MS attacks are detectable by principled checks, and formulate a necessary set of requirements that a practical MS attack must satisfy. Next, we propose SEER, a novel attack framework that satisfies these requirements. The key insight of SEER is the use of a secret decoder, jointly trained with the shared model. We show that SEER can steal user data from gradients of realistic networks, even for large batch sizes of up to 512 and under secure aggregation. Our work is a promising step towards assessing the true vulnerability of federated learning in real-world settings.

Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical aspects of backdoor attacks and dataset distillation based on kernel methods. We introduce two new theory-driven trigger pattern generation methods specialized for dataset distillation. Following a comprehensive set of analyses and experiments, we show that our optimization-based trigger design framework informs effective backdoor attacks on dataset distillation. Notably, datasets poisoned by our designed trigger prove resilient against conventional backdoor attack detection and mitigation methods. Our empirical results validate that the triggers developed using our approaches are proficient at executing resilient backdoor attacks.

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues, for the first time, we formulate backdoor injection as a lightweight knowledge editing problem, and introduce the BadEdit attack framework. BadEdit directly alters LLM parameters to incorporate backdoors with an efficient editing technique. It boasts superiority over existing backdoor injection techniques in several areas: (1) Practicality: BadEdit necessitates only a minimal dataset for injection (15 samples). (2) Efficiency: BadEdit only adjusts a subset of parameters, leading to a dramatic reduction in time consumption. (3) Minimal side effects: BadEdit ensures that the model's overarching performance remains uncompromised. (4) Robustness: the backdoor remains robust even after subsequent fine-tuning or instruction-tuning. Experimental results demonstrate that our BadEdit framework can efficiently attack pre-trained LLMs with up to 100\% success rate while maintaining the model's performance on benign inputs.

In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have been introduced for identifying AI-generated images, with watermarking emerging as a promising approach. In this paper, we analyze the robustness of various AI-image detectors including watermarking and classifier-based deepfake detectors. For watermarking methods that introduce subtle image perturbations (i.e., low perturbation budget methods), we reveal a fundamental trade-off between the evasion error rate (i.e., the fraction of watermarked images detected as non-watermarked ones) and the spoofing error rate (i.e., the fraction of non-watermarked images detected as watermarked ones) upon an application of a diffusion purification attack. In this regime, we also empirically show that diffusion purification effectively removes watermarks with minimal changes to images. For high perturbation watermarking methods where notable changes are applied to images, the diffusion purification attack is not effective. In this case, we develop a model substitution adversarial attack that can successfully remove watermarks. Moreover, we show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images (potentially obscene) identified as watermarked ones, damaging the reputation of the developers. In particular, by just having black-box access to the watermarking method, we show that one can generate a watermarked noise image which can be added to the real images to have them falsely flagged as watermarked ones. Finally, we extend our theory to characterize a fundamental trade-off between the robustness and reliability of classifier-based deep fake detectors and demonstrate it through experiments. Code is available at https://github.com/mehrdadsaberi/watermark_robustness.

Saliency-based representation visualization (SRV) ($e.g.$, Grad-CAM) is one of the most classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity and efficiency. It can be used to interpret deep neural networks by locating saliency areas contributing the most to their predictions. However, it is difficult to automatically measure and evaluate the performance of SRV methods due to the lack of ground-truth salience areas of samples. In this paper, we revisit the backdoor-based SRV evaluation, which is currently the only feasible method to alleviate the previous problem. We first reveal its \emph{implementation limitations} and \emph{unreliable nature} due to the trigger generalization of existing backdoor watermarks. Given these findings, we propose a generalization-limited backdoor watermark (GLBW), based on which we design a more faithful XAI evaluation. Specifically, we formulate the training of watermarked DNNs as a min-max problem, where we find the `worst' potential trigger (with the highest attack effectiveness and differences from the ground-truth trigger) via inner maximization and minimize its effects and the loss over benign and poisoned samples via outer minimization in each iteration. In particular, we design an adaptive optimization method to find desired potential triggers in each inner maximization. Extensive experiments on benchmark datasets are conducted, verifying the effectiveness of our generalization-limited watermark. Our codes are available at \url{https://github.com/yamengxi/GLBW}.

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the form of backdoor attacks, wherein the model will output unintended malicious content under specific backdoor-triggered conditions during inference. Traditional methods for launching backdoor attacks involve either contaminating the training dataset with backdoored instances or directly manipulating the model parameters during deployment. However, these approaches are not practical for commercial LLMs that typically operate via API access. In this paper, we propose BadChain, the first backdoor attack against LLMs employing COT prompting, which does not require access to the training dataset or model parameters and imposes low computational overhead. BadChain leverages the inherent reasoning capabilities of LLMs by inserting a backdoor reasoning step into the sequence of reasoning steps of the model output, thereby altering the final response when a backdoor trigger is embedded in the query prompt. In particular, a subset of demonstrations will be manipulated to incorporate a backdoor reasoning step in COT prompting. Consequently, given any query prompt containing the backdoor trigger, the LLM will be misled to output unintended content. Empirically, we show the effectiveness of BadChain for two COT strategies across four LLMs (Llama2, GPT-3.5, PaLM2, and GPT-4) and six complex benchmark tasks encompassing arithmetic, commonsense, and symbolic reasoning. We show that the baseline backdoor attacks designed for simpler tasks such as semantic classification will fail on these complicated tasks. In addition, our findings reveal that LLMs endowed with stronger reasoning capabilities exhibit higher susceptibility to BadChain, exemplified by a high average attack success rate of 97.0\% across the six benchmark tasks on GPT-4. We also demonstrate the interpretability of BadChain by showing that the relationship between the trigger and the backdoor reasoning step can be well-explained based on the output of the backdoored model. Finally, we propose two defenses based on shuffling and demonstrate their overall ineffectiveness against BadChain. Therefore, BadChain remains a severe threat to LLMs, underscoring the urgency for the development of robust and effective future defenses.

When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-world applications. While they have been intensively studied in classification, backdoor attacks on semantic segmentation have been largely overlooked. Unlike classification, semantic segmentation aims to classify every pixel within a given image. In this work, we explore backdoor attacks on segmentation models to misclassify all pixels of a victim class by injecting a specific trigger on non-victim pixels during inferences, which is dubbed Influencer Backdoor Attack (IBA). IBA is expected to maintain the classification accuracy of non-victim pixels and mislead classifications of all victim pixels in every single inference and could be easily applied to real-world scenes. Based on the context aggregation ability of segmentation models, we proposed a simple, yet effective, Nearest-Neighbor trigger injection strategy. We also introduce an innovative Pixel Random Labeling strategy which maintains optimal performance even when the trigger is placed far from the victim pixels. Our extensive experiments reveal that current segmentation models do suffer from backdoor attacks, demonstrate IBA real-world applicability, and show that our proposed techniques can further increase attack performance.

Recent studies revealed that using third-party models may lead to backdoor threats, where adversaries can maliciously manipulate model predictions based on backdoors implanted during model training. Arguably, backdoor trigger inversion (BTI), which generates trigger patterns of given benign samples for a backdoored model, is the most critical module for backdoor defenses used in these scenarios. With BTI, defenders can remove backdoors by fine-tuning based on generated poisoned samples with ground-truth labels or deactivate backdoors by removing trigger patterns during the inference process. However, we find that existing BTI methods suffer from relatively poor performance, $i.e.$, their generated triggers are significantly different from the ones used by the adversaries even in the feature space. We argue that it is mostly because existing methods require to 'extract' backdoor features at first, while this task is very difficult since defenders have no information ($e.g.$, trigger pattern or target label) about poisoned samples. In this paper, we explore BTI from another perspective where we decouple benign features instead of decoupling backdoor features directly. Specifically, our method consists of two main steps, including \textbf{(1)} decoupling benign features and \textbf{(2)} trigger inversion by minimizing the differences between benign samples and their generated poisoned version in decoupled benign features while maximizing the differences in remaining backdoor features. In particular, our method is more efficient since it doesn't need to `scan' all classes to speculate the target label, as required by existing BTI. We also exploit our BTI module to further design backdoor-removal and pre-processing-based defenses. Extensive experiments on benchmark datasets demonstrate that our defenses can reach state-of-the-art performances.

Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increasingly crucial. A major stream of watermarking strategies implants verifiable backdoor triggers by poisoning training samples, but these are often unrealistic due to data privacy and safety concerns and are vulnerable to minor model changes such as fine-tuning. To overcome these challenges, we propose a safe and robust backdoor-based watermark injection technique that leverages the diverse knowledge from a single out-of-distribution (OoD) image, which serves as a secret key for IP verification. The independence of training data makes it agnostic to third-party promises of IP security. We induce robustness via random perturbation of model parameters during watermark injection to defend against common watermark removal attacks, including fine-tuning, pruning, and model extraction. Our experimental results demonstrate that the proposed watermarking approach is not only time- and sample-efficient without training data, but also robust against the watermark removal attacks above.

Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret watermarking key. A core security property of watermarking is robustness, which states that an attacker can only evade detection by substantially degrading image quality. Assessing robustness requires designing an adaptive attack for the specific watermarking algorithm. When evaluating watermarking algorithms and their (adaptive) attacks, it is challenging to determine whether an adaptive attack is optimal, i.e., the best possible attack. We solve this problem by defining an objective function and then approach adaptive attacks as an optimization problem. The core idea of our adaptive attacks is to replicate secret watermarking keys locally by creating surrogate keys that are differentiable and can be used to optimize the attack's parameters. We demonstrate for Stable Diffusion models that such an attacker can break all five surveyed watermarking methods at no visible degradation in image quality. Optimizing our attacks is efficient and requires less than 1 GPU hour to reduce the detection accuracy to 6.3% or less. Our findings emphasize the need for more rigorous robustness testing against adaptive, learnable attackers.

Node labels for graphs are usually generated using an automated process or crowd-sourced from human users. This opens up avenues for malicious users to compromise the training labels, making it unwise to blindly rely on them. While robustness against noisy labels is an active area of research, there are only a handful of papers in the literature that address this for graph-based data. Even more so, the effects of adversarial label perturbations is sparsely studied. More critically, we reveal that the entire literature on label poisoning for GNNs is plagued by serious evaluation pitfalls. Thus making it hard to conclude how robust GNNs are against label perturbations. After course correcting the state of label poisoning attacks with our faithful evaluation, we identify a discrepancy in attack efficiency of $\sim9\%$ on average. Additionally, we introduce two new simple yet effective attacks that are significantly stronger (up to $\sim8\%$) than the previous strongest attack. Our strongest proposed attack can be efficiently computed and is theoretically backed.

Deep neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to specific training data. Existing defense strategies primarily focus on using reverse engineering to reproduce the backdoor trigger generated by attackers and subsequently repair the DNN model by adding the trigger into inputs and fine-tuning the model with ground truth labels. However, once the trigger generated by the attackers is complex and invisible, the defender cannot reproduce the trigger successfully then the DNN model will not be repaired, as the trigger is not effectively removed. In this work, we propose Adversarial Feature Map Pruning for Backdoor (FMP) to mitigate backdoor from the DNN. Unlike existing defense strategies, which focus on reproducing backdoor triggers, FMP attempts to prune backdoor feature maps, which are trained to extract backdoor information from inputs. After pruning these backdoor feature maps, FMP will fine-tune the model with a secure subset of training data. Our experiments demonstrate that, compared to existing defense strategies, FMP can effectively reduce the Attack Success Rate (ASR) even against the most complex and invisible attack triggers (e.g., FMP decreases the ASR to 2.86% in CIFAR10, which is 19.2% to 65.41% lower than baselines). Second, unlike conventional defense methods that tend to exhibit low robust accuracy (that is, the accuracy of the model on poisoned data), FMP achieves a higher RA, indicating its superiority in maintaining model performance while mitigating the effects of backdoor attacks (e.g., FMP obtains 87.40% RA in CIFAR10). Our code is publicly available at: https://github.com/hku-systems/FMP.

Backdoor attacks pose a significant security risk to machine learning applications due to their stealthy nature and potentially serious consequences. Such attacks involve embedding triggers within a learning model with the intention of causing malicious behavior when an active trigger is present while maintaining regular functionality without it. This paper derives a fundamental understanding of backdoor attacks that applies to both discriminative and generative models, including diffusion models and large language models. We evaluate the effectiveness of any backdoor attack incorporating a constant trigger, by establishing tight lower and upper boundaries for the performance of the compromised model on both clean and backdoor test data. The developed theory answers a series of fundamental but previously underexplored problems, including (1) what are the determining factors for a backdoor attack's success, (2) what is the direction of the most effective backdoor attack, and (3) when will a human-imperceptible trigger succeed. We demonstrate the theory by conducting experiments using benchmark datasets and state-of-the-art backdoor attack scenarios. Our code is available \href{https://github.com/KeyWgh/DemystifyBackdoor}{here}.