Backdoor Attacks

Distributed learning is an effective approach to accelerate model training by using parallel computing power of multiple workers. However, substantial communication delays arise between workers and a parameter server due to the massive costs associated with communicating gradients. SignSGD with majority voting (signSGD-MV) is a simple yet effective optimizer that reduces communication costs through sign quantization, but its convergence rate significantly decreases when adversarial workers arbitrarily manipulate datasets or local gradient updates. In this paper, we consider a distributed learning problem where the workforce comprises a mixture of honest and adversarial workers. In this setting, we show that the convergence rate can remain invariant as long as the number of honest workers providing trustworthy local updates to the parameter server exceeds the number of adversarial workers. The key idea behind this counter-intuitive result is our novel aggregation method, signSGD with federated defense (signSGD-FD). Unlike traditional approaches, signSGD-FD utilizes the gradient information sent by adversarial workers with appropriate weights, obtained through gradient sign decoding. Experimental results demonstrate that signSGD-FD achieves superior convergence rates compared to traditional algorithms in various adversarial attack scenarios.

Contrastive Language-Image Pre-training (CLIP) on large image-caption datasets has achieved remarkable success in zero-shot classification and enabled transferability to new domains. However, CLIP is extremely more vulnerable to targeted data poisoning and backdoor attacks compared to supervised learning. Perhaps surprisingly, poisoning 0.0001% of CLIP pre-training data is enough to make targeted data poisoning attacks successful. This is four orders of magnitude smaller than what is required to poison supervised models. Despite this vulnerability, existing methods are very limited in defending CLIP models during pre-training. In this work, we propose a strong defense, SAFECLIP, to safely pre-train CLIP against targeted data poisoning and backdoor attacks. SAFECLIP warms up the model by applying unimodal contrastive learning (CL) on image and text modalities separately. Then, it divides the data into safe and risky sets by applying a Gaussian Mixture Model to the cosine similarity of image-caption pair representations. SAFECLIP pre-trains the model by applying the CLIP loss to the safe set and applying unimodal CL to image and text modalities of the risky set separately. By gradually increasing the size of the safe set during pre-training, SAFECLIP effectively breaks targeted data poisoning and backdoor attacks without harming the CLIP performance. Our extensive experiments on CC3M, Visual Genome, and MSCOCO demonstrate that SAFECLIP significantly reduces the success rate of targeted data poisoning attacks from 93.75% to 0% and that of various backdoor attacks from up to 100% to 0%, without harming CLIP’s performance.

Recently, diffusion models have become popular tools for image synthesis due to their high-quality outputs. However, like other large models, they may leak private information about their training data. Here, we demonstrate a privacy vulnerability of diffusion models through a *membership inference (MI) attack*, which aims to identify whether a target example belongs to the training set when given the trained diffusion model. Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training. This allows us to define a granular hypothesis test for determining the membership of a point in the training set, based on thresholding the reconstruction loss of that point using a custom threshold tailored to the example. We also provide a simple bootstrap technique that takes a majority membership prediction over ''a bag of weak attackers'' which improves the accuracy over individual quantile regression models. We show that our attack outperforms the prior state-of-the-art attack while being substantially less computationally expensive --- prior attacks required training multiple ''shadow models'' with the same architecture as the model under attack, whereas our attack requires training only much smaller models.

In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability of adversarial prompts. The computational efficiency of BEAST facilitates us to investigate its applications on LMs for jailbreaking, eliciting hallucinations, and privacy attacks. Our gradient-free targeted attack can jailbreak aligned LMs with high attack success rates within one minute. For instance, BEAST can jailbreak Vicuna-7B-v1.5 under one minute with a success rate of 89% when compared to a gradient-based baseline that takes over an hour to achieve 70% success rate using a single Nvidia RTX A6000 48GB GPU. BEAST can also generate adversarial suffixes for successful jailbreaks that can transfer to unseen prompts and unseen models such as GPT-4-Turbo. Additionally, we discover a unique outcome wherein our untargeted attack induces hallucinations in LM chatbots. Through human evaluations, we find that our untargeted attack causes Vicuna-7B-v1.5 to produce $\sim$15% more incorrect outputs when compared to LM outputs in the absence of our attack. We also learn that 22% of the time, BEAST causes Vicuna to generate outputs that are not relevant to the original prompt. Further, we use BEAST to generate adversarial prompts in a few seconds that can boost the performance of existing membership inference attacks for LMs. We believe that our fast attack, BEAST, has the potential to accelerate research in LM security and privacy.

Pixel-wise regression tasks (e.g., monocular depth estimation (MDE) and optical flow estimation (OFE)) have been widely involved in our daily life in applications like autonomous driving, augmented reality and video composition. Although certain applications are security-critical or bear societal significance, the adversarial robustness of such models are not sufficiently studied, especially in the black-box scenario. In this work, we introduce the first unified black-box adversarial patch attack framework against pixel-wise regression tasks, aiming to identify the vulnerabilities of these models under query-based black-box attacks. We propose a novel square-based adversarial patch optimization framework and employ probabilistic square sampling and score-based gradient estimation techniques to generate the patch effectively and efficiently, overcoming the scalability problem of previous black-box patch attacks. Our attack prototype, named BadPart, is evaluated on both MDE and OFE tasks, utilizing a total of 7 models. BadPart surpasses 3 baseline methods in terms of both attack performance and efficiency. We also apply BadPart on the Google online service for portrait depth estimation, causing 43.5% relative distance error with 50K queries. State-of-the-art (SOTA) countermeasures cannot defend our attack effectively.

Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private for security and privacy issues, while only the pretrained weight is available to the public. In such scenarios, existing methods that assume accessibility to the original data become inapplicable. Thus we investigate the pivotal problem of data-free adversarial robustness, where we try to achieve adversarial robustness without accessing any real data. Through a preliminary study, we highlight the severity of the problem by showing that robustness without the original dataset is difficult to achieve, even with similar domain datasets. To address this issue, we propose DataFreeShield, which tackles the problem from two perspectives: surrogate dataset generation and adversarial training using the generated data. Through extensive validation, we show that DataFreeShield outperforms baselines, demonstrating that the proposed method sets the first entirely data-free solution for the adversarial robustness problem.

Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by a fine-grained modeling of the null hypothesis in our likelihood ratio tests, and effectively leveraging both reference models and reference population data samples. RMIA has superior test power compared with prior methods, throughout the TPR-FPR curve (even at extremely low FPR, as low as 0). Under computational constraints, where only a limited number of pre-trained reference models (as few as 1) are available, and also when we vary other elements of the attack (e.g., data distribution), our method performs exceptionally well, unlike prior attacks that approach random guessing. RMIA lays the groundwork for practical yet accurate data privacy risk assessment in machine learning.

Recent studies have discovered that a deep reinforcement learning (DRL) policy is vulnerable to backdoor attacks. Existing defenses against backdoor attacks either do not consider RL's unique mechanism or make unrealistic assumptions, resulting in limited defense efficacy, practicability, and generalizability. We propose SHINE, a backdoor shielding method specific for DRL. SHINE designs novel policy explanation techniques to identify the backdoor triggers and a policy retraining algorithm to eliminate the impact of the triggers on backdoored agents. We theoretically justify that SHINE guarantees to improve a backdoored agent's performance in a poisoned environment while ensuring its performance difference in the clean environment before and after shielding is bounded. We further conduct extensive experiments that evaluate SHINE against three mainstream DRL backdoor attacks in various benchmark RL environments. Our results show that SHINE significantly outperforms existing defenses in mitigating these backdoor attacks.

Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct communication between non-neighbor nodes might lead to the belief that users cannot infer precise information about the data of others. In this work, we demonstrate the opposite, by proposing the first attack against D-GD that enables a user (or set of users) to reconstruct the private data of other users outside their immediate neighborhood. Our approach is based on a reconstruction attack against the gossip averaging protocol, which we then extend to handle the additional challenges raised by D-GD. We validate the effectiveness of our attack on real graphs and datasets, showing that the number of users compromised by a single or a handful of attackers is often surprisingly large. We empirically investigate some of the factors that affect the performance of the attack, namely the graph topology, the number of attackers, and their position in the graph.

Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulnerable to multi-step adversarial attacks. However, the underlying factors that lead to the distortion of decision boundaries remain unclear. In this work, we delve into the specific changes within different DNN layers and discover that during CO, the former layers are more susceptible, experiencing earlier and greater distortion, while the latter layers show relative insensitivity. Our analysis further reveals that this increased sensitivity in former layers stems from the formation of $\textit{pseudo-robust shortcuts}$, which alone can impeccably defend against single-step adversarial attacks but bypass genuine-robust learning, resulting in distorted decision boundaries. Eliminating these shortcuts can partially restore robustness in DNNs from the CO state, thereby verifying that dependence on them triggers the occurrence of CO. This understanding motivates us to implement adaptive weight perturbations across different layers to hinder the generation of $\textit{pseudo-robust shortcuts}$, consequently mitigating CO. Extensive experiments demonstrate that our proposed method, $\textbf{L}$ayer-$\textbf{A}$ware Adversarial Weight $\textbf{P}$erturbation (LAP), can effectively prevent CO and further enhance robustness.

Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger. In this paper, we investigate how to protect diffusion models from this dangerous threat. Specifically, we propose **TERD**, a backdoor defense framework that builds unified modeling for current attacks, which enables us to derive an accessible reversed loss. A trigger reversion strategy is further employed: an initial approximation of the trigger through noise sampled from a prior distribution, followed by refinement through differential multi-step samplers. Additionally, with the reversed trigger, we propose backdoor detection from the noise space, introducing the first backdoor input detection approach for diffusion models and a novel model detection algorithm that calculates the KL divergence between reversed and benign distributions. Extensive evaluations demonstrate that TERD secures a 100% True Positive Rate (TPR) and True Negative Rate (TNR) across datasets of varying resolutions. TERD also demonstrates nice adaptability to other Stochastic Differential Equation (SDE)-based models. Our code is available at https://github.com/PKU-ML/TERD.

The efficient and theoretically sound uncertainty quantification is crucial for building trust in deep learning models. This has spurred a growing interest in conformal prediction (CP), a powerful technique that provides a model-agnostic and distribution-free method for obtaining conformal prediction sets with theoretical guarantees. However, the vulnerabilities of such CP methods with regard to dedicated data poisoning attacks have not been studied previously. To bridge this gap, for the first time, we in this paper propose a new class of black-box data poisoning attacks against CP, where the adversary aims to cause the desired manipulations of some specific examples' prediction uncertainty results (instead of misclassifications). Additionally, we design novel optimization frameworks for our proposed attacks. Further, we conduct extensive experiments to validate the effectiveness of our attacks on various settings (e.g., the full and split CP settings). Notably, our extensive experiments show that our attacks are more effective in manipulating uncertainty results than traditional poisoning attacks that aim at inducing misclassifications, and existing defenses against conventional attacks are ineffective against our proposed attacks.

We have developed a new framework based on the theory of causal inference to protect language models against backdoor attacks. Backdoor attackers can poison language models with different types of triggers, such as words, sentences, grammar, and style, enabling them to selectively modify the decision-making of the victim model. However, existing defense approaches are only effective when the backdoor attack form meets specific assumptions, making it difficult to counter diverse backdoor attacks. We propose a new defense framework **F**ront-door **A**djustment for **B**ackdoor **E**limination (FABE) based on causal reasoning that does not rely on assumptions about the form of triggers. This method effectively differentiates between spurious and legitimate associations by creating a 'front door' that maps out the actual causal relationships. The term 'front door' refers to a text that retains the semantic equivalence of the initial input, which is generated by an additional, fine-tuned language model, denoted as the defense model. Our defense experiments against various attack methods at the token, sentence, and syntactic levels reduced the attack success rate from 93.63% to 15.12%, improving the defense effect by 2.91 times compared to the best baseline result of 66.61%, achieving state-of-the-art results. Through ablation study analysis, we analyzed the effect of each module in FABE, demonstrating the importance of complying with the front-door criterion and front-door adjustment formula, which also explains why previous methods failed. Our code to reproduce the experiments is available at: https://github.com/lyr17/Frontdoor-Adjustment-Backdoor-Elimination.

The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnerabilities of these solutions are underexplored. In this study, we formalized the Copyright Infringement Attack on generative AI models and proposed a backdoor attack method, SilentBadDiffusion, to induce copyright infringement without requiring access to or control over training processes. Our method strategically embeds connections between pieces of copyrighted information and text references in poisoning data while carefully dispersing that information, making the poisoning data inconspicuous when integrated into a clean dataset. Our experiments show the stealth and efficacy of the poisoning data. When given specific text prompts, DMs trained with a poisoning ratio of 0.20% can produce copyrighted images. Additionally, the results reveal that the more sophisticated the DMs are, the easier the success of the attack becomes. These findings underline potential pitfalls in the prevailing copyright protection strategies and underscore the necessity for increased scrutiny to prevent the misuse of DMs.

The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learning, adversarial learning, and data poisoning. Unlike other data poison attacks, the backdoor attack has the special property that the poisoned triggers are contained in both the training set and the test set and the purpose of the attack is two-fold. To our knowledge, the generalization bound for the backdoor attack has not been established. In this paper, we fill this gap by deriving algorithm-independent generalization bounds in the clean-label backdoor attack scenario. Precisely, based on the goals of backdoor attack, we give upper bounds for the clean sample population errors and the poison population errors in terms of the empirical error on the poisoned training dataset. Furthermore, based on the theoretical result, a new clean-label backdoor attack is proposed that computes the poisoning trigger by combining adversarial noise and indiscriminate poison. We show its effectiveness in a variety of settings.

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level backdoor detection (dubbed IBD-PSC) as a `firewall' to filter out malicious testing images. Our method is motivated by an intriguing phenomenon, i.e., parameter-oriented scaling consistency (PSC), where the prediction confidences of poisoned samples are significantly more consistent than those of benign ones when amplifying model parameters. In particular, we provide theoretical analysis to safeguard the foundations of the PSC phenomenon. We also design an adaptive method to select BN layers to scale up for effective detection. Extensive experiments are conducted on benchmark datasets, verifying the effectiveness and efficiency of our IBD-PSC method and its resistance to adaptive attacks. Codes are available at https://github.com/THUYimingLi/BackdoorBox.

Federated Learning (FL) faces threats from model poisoning attacks. Existing defenses, typically relying on cross-client/global information to mitigate these attacks, fall short when faced with non-IID data distributions and/or a large number of malicious clients. To address these challenges, we present FedREDefense. Unlike existing methods, it doesn't hinge on similar distributions across clients or a predominant presence of benign clients. Instead, it assesses the likelihood that a client's model update is a product of genuine training, solely based on the characteristics of the model update itself. Our key finding is that model updates stemming from genuine training can be approximately reconstructed with some distilled local knowledge, while those from deliberate handcrafted model poisoning attacks cannot. Drawing on this distinction, FedREDefense identifies and filters out malicious clients based on the discrepancies in their model update Reconstruction Errors. Empirical tests on three benchmark datasets confirm that FedREDefense successfully filters model poisoning attacks in FL—even in scenarios with high non-IID degrees and large numbers of malicious clients.

Backdoor defense is crucial to ensure the safety and robustness of machine learning models when under attack. However, most existing methods specialize in either the detection or removal of backdoors, but seldom both. While few works have addressed both, these methods rely on strong assumptions or entail significant overhead costs, such as the need of task-specific samples for detection and model retraining for removal. Hence, the key challenge is how to reduce overhead and relax unrealistic assumptions. In this work, we propose two Energy-Based BAckdoor defense methods, called EBBA and EBBA+, that can achieve both backdoored model detection and backdoor removal with low overhead. Our contributions are twofold: First, we offer theoretical analysis for our observation that a predefined target label is more likely to occur among the top results for various samples. Inspired by this, we develop an enhanced energy-based technique, called EBBA, to detect backdoored models without task-specific samples (i.e., samples from any tasks). Secondly, we theoretically analyze that after data corruption, the original clean label of a poisoned sample is more likely to be predicted as a top output by the model, a sharp contrast to clean samples. Accordingly, we extend EBBA to develop EBBA+, a new transferred energy approach to efficiently detect poisoned images and remove backdoors without model retraining. Extensive experiments on multiple benchmark datasets demonstrate the superior performance of our methods over baselines in both backdoor detection and removal. Notably, the proposed methods can effectively detect backdoored model and poisoned images as well as remove backdoors at the same time.

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural Networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings.

Despite the great progress of 3D vision, data privacy and security issues in 3D deep learning are not explored systematically. In the domain of 2D images, many availability attacks have been proposed to prevent data from being illicitly learned by unauthorized deep models. However, unlike images represented on a fixed dimensional grid, point clouds are characterized as unordered and unstructured sets, posing a significant challenge in designing an effective availability attack for 3D deep learning. In this paper, we theoretically show that extending 2D availability attacks directly to 3D point clouds under distance regularization is susceptible to the degeneracy, rendering the generated poisons weaker or even ineffective. This is because in bi-level optimization, introducing regularization term can result in update directions out of control. To address this issue, we propose a novel Feature Collision Error-Minimization (FC-EM) method, which creates additional shortcuts in the feature space, inducing different update directions to prevent the degeneracy of bi-level optimization. Moreover, we provide a theoretical analysis that demonstrates the effectiveness of the FC-EM attack. Extensive experiments on typical point cloud datasets, 3D intracranial aneurysm medical dataset, and 3D face dataset verify the superiority and practicality of our approach.