Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to perturbations poses a significant threat to their reliability in real-world applications. Despite often being imperceptible to humans, these perturbations can drastically alter model outputs, leading to erroneous interpretations and decisions. This paper introduces DiffCAP, a novel diffusion-based purification strategy that can effectively neutralize adversarial corruptions in VLMs. We observe that adding minimal noise to an adversarially corrupted image significantly alters its latent embedding with respect to VLMs. Building on this insight, DiffCAP cumulatively injects random Gaussian noise into adversarially perturbed input data. This process continues until the embeddings of two consecutive noisy images reach a predefined similarity threshold, indicating a potential approach to neutralize the adversarial effect. Subsequently, a pretrained diffusion model is employed to denoise the stabilized image, recovering a clean representation suitable for the VLMs to produce an output. Through extensive experiments across six datasets with three VLMs under varying attack strengths in three task scenarios, we show that DiffCAP consistently outperforms existing defense techniques by a substantial margin. Notably, DiffCAP significantly reduces both hyperparameter tuning complexity and the required diffusion time, thereby accelerating the denoising process. Equipped with strong theoretical and empirical support, DiffCAP provides a robust and practical solution for securely deploying VLMs in adversarial environments.
Recent advances in large vision-language models (LVLMs) have showcased their remarkable capabilities across a wide range of multimodal vision-language tasks. However, these models remain vulnerable to visual adversarial attacks, which can substantially compromise their performance. Despite their potential impact, the development of effective methods for purifying such adversarial examples has received relatively limited attention. In this paper, we introduce F3, a novel adversarial purification framework that employs a counterintuitive "fighting fire with fire" strategy: intentionally introducing simple perturbations to adversarial examples to mitigate their harmful effects. Specifically, F3 leverages cross-modal attentions derived from randomly perturbed adversary examples as reference targets. By injecting noise into these adversarial examples, F3 effectively refines their attention, resulting in cleaner and more reliable model outputs. Remarkably, this seemingly paradoxical approach of employing noise to counteract adversarial attacks yields impressive purification results. Furthermore, F3 offers several distinct advantages: it is training-free and straightforward to implement, and exhibits significant computational efficiency improvements compared to existing purification methods. These attributes render F3 particularly suitable for large-scale industrial applications where both robust performance and operational efficiency are critical priorities. The code will be made publicly available.
Recent findings suggest that diffusion models significantly enhance empirical adversarial robustness. While some intuitive explanations have been proposed, the precise mechanisms underlying these improvements remain unclear. In this work, we systematically investigate how and how well diffusion models improve adversarial robustness. First, we observe that diffusion models intriguingly increase, rather than decrease, the $\ell_p$ distance to clean samples--challenging the intuition that purification denoises inputs closer to the original data. Second, we find that the purified images are heavily influenced by the internal randomness of diffusion models, where a compression effect arises within each randomness configuration. Motivated by this observation, we evaluate robustness under fixed randomness and find that the improvement drops to approximately 24% on CIFAR-10--substantially lower than prior reports approaching 70%. Importantly, we show that this remaining robustness gain strongly correlates with the model's ability to compress the input space, revealing the compression rate as a reliable robustness indicator without requiring gradient-based analysis. Our findings provide novel insights into the mechanisms underlying diffusion-based purification, and offer guidance for developing more effective and principled adversarial purification systems.
Adversarial attacks have become a well-explored domain, frequently serving as evaluation baselines for model robustness. Among these, black-box attacks based on transferability have received significant attention due to their practical applicability in real-world scenarios. Traditional black-box methods have generally focused on improving the optimization framework (e.g., utilizing momentum in MI-FGSM) to enhance transferability, rather than examining the dependency on surrogate white-box model architectures. Recent state-of-the-art approach DiffPGD has demonstrated enhanced transferability by employing diffusion-based adversarial purification models for adaptive attacks. The inductive bias of diffusion-based adversarial purification aligns naturally with the adversarial attack process, where both involving noise addition, reducing dependency on surrogate white-box model selection. However, the denoising process of diffusion models incurs substantial computational costs through chain rule derivation, manifested in excessive VRAM consumption and extended runtime. This progression prompts us to question whether introducing diffusion models is necessary. We hypothesize that a model sharing similar inductive bias to diffusion-based adversarial purification, combined with an appropriate loss function, could achieve comparable or superior transferability while dramatically reducing computational overhead. In this paper, we propose a novel loss function coupled with a unique surrogate model to validate our hypothesis. Our approach leverages the score of the time-dependent classifier from classifier-guided diffusion models, effectively incorporating natural data distribution knowledge into the adversarial optimization process. Experimental results demonstrate significantly improved transferability across diverse model architectures while maintaining robustness against diffusion-based defenses.
Despite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has emerged as a promising defense strategy. To achieve this, state-of-the-art methods leverage diffusion models that inject Gaussian noise during a forward process to dilute adversarial perturbations, followed by a denoising step to restore clean samples before classification. In this work, we propose FlowPure, a novel purification method based on Continuous Normalizing Flows (CNFs) trained with Conditional Flow Matching (CFM) to learn mappings from adversarial examples to their clean counterparts. Unlike prior diffusion-based approaches that rely on fixed noise processes, FlowPure can leverage specific attack knowledge to improve robustness under known threats, while also supporting a more general stochastic variant trained on Gaussian perturbations for settings where such knowledge is unavailable. Experiments on CIFAR-10 and CIFAR-100 demonstrate that our method outperforms state-of-the-art purification-based defenses in preprocessor-blind and white-box scenarios, and can do so while fully preserving benign accuracy in the former. Moreover, our results show that not only is FlowPure a highly effective purifier but it also holds a strong potential for adversarial detection, identifying preprocessor-blind PGD samples with near-perfect accuracy.
The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of distribution information about adversarial perturbations in the pixel domain, it is often unavoidable to damage normal semantics. We turn to the frequency domain perspective, decomposing the image into amplitude spectrum and phase spectrum. We find that for both spectra, the damage caused by adversarial perturbations tends to increase monotonically with frequency. This means that we can extract the content and structural information of the original clean sample from the frequency components that are less damaged. Meanwhile, theoretical analysis indicates that existing purification methods indiscriminately damage all frequency components, leading to excessive damage to the image. Therefore, we propose a purification method that can eliminate adversarial perturbations while maximizing the preservation of the content and structure of the original image. Specifically, at each time step during the reverse process, for the amplitude spectrum, we replace the low-frequency components of the estimated image's amplitude spectrum with the corresponding parts of the adversarial image. For the phase spectrum, we project the phase of the estimated image into a designated range of the adversarial image's phase spectrum, focusing on the low frequencies. Empirical evidence from extensive experiments demonstrates that our method significantly outperforms most current defense methods.
Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained on, limiting its ability to generalize to unseen threat models. Adversarial purification offers an alternative by leveraging a generative model to remove perturbations before classification. Since the purifier is trained independently of both the classifier and the threat models, it is better equipped to handle previously unseen attack scenarios. Diffusion models have proven highly effective for noise purification, not only in countering pixel-wise adversarial perturbations but also in addressing non-adversarial data shifts. In this study, we broaden the focus beyond pixel-wise robustness to explore the extent to which purification can mitigate both spectral and spatial adversarial attacks. Our findings highlight its effectiveness in handling diverse distortion patterns across low- to high-frequency regions.
State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. To protect against this scenario, Adversarial Training (AT) and Adversarial Distillation (AD) include adversarial examples during the training phase, and Adversarial Purification uses a generative model to reconstruct all the images given to the classifier. This paper considers an even more realistic evaluation scenario: gray-box attacks, which assume that the attacker knows the architecture and the dataset used to train the target network, but cannot access its gradients. We provide empirical evidence that models are vulnerable to gray-box attacks and propose LISArD, a defense mechanism that does not increase computational and temporal costs but provides robustness against gray-box and white-box attacks without including AT. Our method approximates a cross-correlation matrix, created with the embeddings of perturbed and clean images, to a diagonal matrix while simultaneously conducting classification learning. Our results show that LISArD can effectively protect against gray-box attacks, can be used in multiple architectures, and carries over its resilience to the white-box scenario. Also, state-of-the-art AD models underperform greatly when removing AT and/or moving to gray-box settings, highlighting the lack of robustness from existing approaches to perform in various conditions (aside from white-box settings). All the source code is available at https://github.com/Joana-Cabral/LISArD.
Deep neural networks are known to be vulnerable to well-designed adversarial attacks. Although numerous defense strategies have been proposed, many are tailored to the specific attacks or tasks and often fail to generalize across diverse scenarios. In this paper, we propose Tensor Network Purification (TNP), a novel model-free adversarial purification method by a specially designed tensor network decomposition algorithm. TNP depends neither on the pre-trained generative model nor the specific dataset, resulting in strong robustness across diverse adversarial scenarios. To this end, the key challenge lies in relaxing Gaussian-noise assumptions of classical decompositions and accommodating the unknown distribution of adversarial perturbations. Unlike the low-rank representation of classical decompositions, TNP aims to reconstruct the unobserved clean examples from an adversarial example. Specifically, TNP leverages progressive downsampling and introduces a novel adversarial optimization objective to address the challenge of minimizing reconstruction error but without inadvertently restoring adversarial perturbations. Extensive experiments conducted on CIFAR-10, CIFAR-100, and ImageNet demonstrate that our method generalizes effectively across various norm threats, attack types, and tasks, providing a versatile and promising adversarial purification technique.
Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models' adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Our code is available at https://github.com/deep-kaixun/VideoPure.
Adversarial training and adversarial purification are two effective and practical defense methods to enhance a model's robustness against adversarial attacks. However, adversarial training necessitates additional training, while adversarial purification suffers from low time efficiency. More critically, current defenses are designed under the perturbation-based adversarial threat model, which is ineffective against the recently proposed unrestricted adversarial attacks. In this paper, we propose an effective and efficient adversarial defense method that counters both perturbation-based and unrestricted adversarial attacks. Our defense is inspired by the observation that adversarial attacks are typically located near the decision boundary and are sensitive to pixel changes. To address this, we introduce adversarial anti-aliasing to mitigate adversarial modifications. Additionally, we propose adversarial super-resolution, which leverages prior knowledge from clean datasets to benignly recover images. These approaches do not require additional training and are computationally efficient without calculating gradients. Extensive experiments against both perturbation-based and unrestricted adversarial attacks demonstrate that our defense method outperforms state-of-the-art adversarial purification methods.
Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions. Adversarial purification has been an effective means to improve DNNs robustness by removing these perturbations before feeding the data into the model. However, it faces significant challenges in preserving key structural and semantic information of data, as the imperceptible nature of adversarial perturbations makes it hard to avoid over-correcting, which can destroy important information and degrade model performance. In this paper, we break away from traditional adversarial purification methods by focusing on the clean data manifold. To this end, we reveal that samples generated by a well-trained generative model are close to clean ones but far from adversarial ones. Leveraging this insight, we propose Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data. Specifically, 1) we propose a \textit{Perceptual consistency restoration} mechanism by minimizing the discrepancy between generated samples and input samples in both pixel and perceptual spaces. 2) To maintain the optimized latent vectors within the valid data manifold, we introduce a \textit{Latent distribution consistency constraint} strategy to align generated samples with the clean data distribution. 3) We also apply a \textit{Latent vector consistency prediction} scheme via an ensemble approach to enhance prediction reliability. CMAP fundamentally addresses adversarial perturbations at their source, providing a robust purification. Extensive experiments on CIFAR-10 and ImageNet-100 show that our CMAP significantly enhances robustness against strong adversarial attacks while preserving high natural accuracy.
Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial noise. In this study, we propose specific generators, defined Multiple Latent Variable Generative Models (MLVGMs), for adversarial purification. These models possess multiple latent variables that naturally disentangle coarse from fine features. Taking advantage of these properties, we autoencode images to maintain class-relevant information, while discarding and re-sampling any detail, including adversarial noise. The procedure is completely training-free, exploring the generalization abilities of pre-trained MLVGMs on the adversarial purification downstream task. Despite the lack of large models, trained on billions of samples, we show that smaller MLVGMs are already competitive with traditional methods, and can be used as foundation models. Official code released at https://github.com/SerezD/gen_adversarial.
Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., the original DDPM sampling is intended for stable generation, which may not be the optimal solution for adversarial purification. Inspired by the stability of the Denoising Diffusion Implicit Model (DDIM), we propose an opposite sampling scheme called random sampling. In brief, random sampling will sample from a random noisy space during each diffusion process, while DDPM and DDIM sampling will continuously sample from the adjacent or original noisy space. Thus, random sampling obtains more randomness and achieves stronger robustness against adversarial attacks. Correspondingly, we also introduce a novel mediator conditional guidance to guarantee the consistency of the prediction under the purified image and clean image input. To expand awareness of guided diffusion purification, we conduct a detailed evaluation with different sampling methods and our random sampling achieves an impressive improvement in multiple settings. Leveraging mediator-guided random sampling, we also establish a baseline method named DiffAP, which significantly outperforms state-of-the-art (SOTA) approaches in performance and defensive stability. Remarkably, under strong attack, our DiffAP even achieves a more than 20% robustness advantage with 10$\times$ sampling acceleration.
Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces imperceptible perturbations to the original speaker's audio waveform, leading to synthesized speech sounds like another person. This vulnerability poses significant security risks, including speaker identity spoofing and unauthorized voice manipulation. This paper investigates two primary defense strategies to address these threats: adversarial training and adversarial purification. Adversarial training enhances the model's robustness by integrating adversarial examples during the training process, thereby improving resistance to such attacks. Adversarial purification, on the other hand, employs diffusion probabilistic models to revert adversarially perturbed audio to its clean form. Experimental results demonstrate that these defense mechanisms can significantly reduce the impact of adversarial perturbations, enhancing the security and reliability of speaker embedding based zero-shot TTS systems in adversarial environments.
Recognizing 3D point cloud plays a pivotal role in many real-world applications. However, deploying 3D point cloud deep learning model is vulnerable to adversarial attacks. Despite many efforts into developing robust model by adversarial training, they may become less effective against emerging attacks. This limitation motivates the development of adversarial purification which employs generative model to mitigate the impact of adversarial attacks. In this work, we highlight the remaining challenges from two perspectives. First, the purification based method requires retraining the classifier on purified samples which introduces additional computation overhead. Moreover, in a more realistic scenario, testing samples arrives in a streaming fashion and adversarial samples are not isolated from clean samples. These challenges motivates us to explore dynamically update model upon observing testing samples. We proposed a test-time purified self-training strategy to achieve this objective. Adaptive thresholding and feature distribution alignment are introduced to improve the robustness of self-training. Extensive results on different adversarial attacks suggest the proposed method is complementary to purification based method in handling continually changing adversarial attacks on the testing data stream.
Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achieving state-of-the-art results in keyword spotting tasks, their effectiveness for more complex tasks such as sentence-level ASR remains unexplored. Additionally, the impact of the number of forward diffusion steps on performance is not well understood. In this paper, we systematically investigate the use of DMs for defending against adversarial attacks on sentences and examine the effect of varying forward diffusion steps. Through comprehensive experiments on the Mozilla Common Voice dataset, we demonstrate that two forward diffusion steps can completely defend against adversarial attacks on sentences. Moreover, we introduce a novel, training-free approach for detecting adversarial attacks by leveraging a pre-trained DM. Our experimental results show that this method can detect adversarial attacks with high accuracy.
Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem. Previous solutions, such as Anti-DreamBooth, add adversarial noise to images to protect them from being used as training data for malicious generation. However, we found that the adversarial noise can be removed by adversarial purification methods such as DiffPure. Therefore, we propose a new adversarial attack method that adds strong perturbation on the high-frequency areas of images to make it more robust to adversarial purification. Our experiment showed that the adversarial images retained noise even after adversarial purification, hindering malicious image generation.
This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial examples. By theoretically characterizing the inherent purification errors associated with the Markov-based diffusion purifications, we introduce LoRID, a novel Low-Rank Iterative Diffusion purification method designed to remove adversarial perturbation with low intrinsic purification errors. LoRID centers around a multi-stage purification process that leverages multiple rounds of diffusion-denoising loops at the early time-steps of the diffusion models, and the integration of Tucker decomposition, an extension of matrix factorization, to remove adversarial noise at high-noise regimes. Consequently, LoRID increases the effective diffusion time-steps and overcomes strong adversarial attacks, achieving superior robustness performance in CIFAR-10/100, CelebA-HQ, and ImageNet datasets under both white-box and black-box settings.
Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise. Although some diffusion-based purification methods have been proposed, for example, DiffPure, those methods are time-consuming. In this paper, we propose One Step Control Purification (OSCP), a diffusion-based purification model that can purify the adversarial image in one Neural Function Evaluation (NFE) in diffusion models. We use Latent Consistency Model (LCM) and ControlNet for our one-step purification. OSCP is computationally friendly and time efficient compared to other diffusion-based purification methods; we achieve defense success rate of 74.19\% on ImageNet, only requiring 0.1s for each purification. Moreover, there is a fundamental incongruence between consistency distillation and adversarial perturbation. To address this ontological dissonance, we propose Gaussian Adversarial Noise Distillation (GAND), a novel consistency distillation framework that facilitates a more nuanced reconciliation of the latent space dynamics, effectively bridging the natural and adversarial manifolds. Our experiments show that the GAND does not need a Full Fine Tune (FFT); PEFT, e.g., LoRA is sufficient.