相关论文: AdvDiff: Generating Unrestricted Adversarial Examp…

Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome. For many real-world engineering problems, the objective function takes the form of a simulator that predicts how the…

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative…

The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…

Deep neural networks have demonstrated remarkable performance across various domains. However, they are vulnerable to adversarial examples, which can lead to erroneous predictions. Generative Adversarial Networks (GANs) can leverage the…

Adversarial examples are commonly viewed as a threat to ConvNets. Here we present an opposite perspective: adversarial examples can be used to improve image recognition models if harnessed in the right manner. We propose AdvProp, an…

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…

Recent advances in GAN and diffusion models have significantly improved the realism and controllability of facial deepfake manipulation, raising serious concerns regarding privacy, security, and identity misuse. Proactive defenses attempt…

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…

Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims to address the challenge of DPM customization when the only…

3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction. However, its per-scene optimization pipeline limits scalability and generalization, and prevents efficient…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

For the past few years, deep generative models have increasingly been used in biological research for a variety of tasks. Recently, they have proven to be valuable for uncovering subtle cell phenotypic differences that are not directly…

Deep neural networks (DNNs) are vulnerable to adversarial perturbation, where an imperceptible perturbation is added to the image that can fool the DNNs. Diffusion-based adversarial purification focuses on using the diffusion model to…

Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy…

Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, guiding diffusion models on graphs under arbitrary reward…

In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detection of DM-generated images, which is critical to prevent…

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

Monocular Depth Estimation (MDE) serves as a core perception module in autonomous driving systems, but it remains highly susceptible to adversarial attacks. Errors in depth estimation may propagate through downstream decision making and…

Adversarial examples are known to mislead deep learning models to incorrectly classify them, even in domains where such models achieve state-of-the-art performance. Until recently, research on both attack and defense methods focused on…