Related papers: DIFFender: Diffusion-Based Adversarial Defense aga…

The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as…

Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world imaging and vision applications, the associated safety…

Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples,…

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse…

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…

Deep learning models are known to be vulnerable to adversarial attacks by injecting sophisticated designed perturbations to input data. Training-time defenses still exhibit a significant performance gap between natural accuracy and robust…

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Despite modifying only a small localized input region, adversarial patches can drastically change the prediction of computer vision models. However, prior methods either cannot perform satisfactorily under targeted attack scenarios or fail…

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

While language models have made many milestones in text inference and classification tasks, they remain susceptible to adversarial attacks that can lead to unforeseen outcomes. Existing works alleviate this problem by equipping language…

Neural Networks are infamously sensitive to small perturbations in their inputs, making them vulnerable to adversarial attacks. This project evaluates the performance of Denoising Diffusion Probabilistic Models (DDPM) as a purification…

Diffusion models have gained significant attention for high-fidelity image generation. Our work investigates the potential of exploiting diffusion models for adversarial robustness in image classification and object detection. Adversarial…

Person detection has attracted great attention in the computer vision area and is an imperative element in human-centric computer vision. Although the predictive performances of person detection networks have been improved dramatically,…

Adversarial patch attacks pose a practical threat to deep learning models by forcing targeted misclassifications through localized perturbations, often realized in the physical world. Existing defenses typically assume prior knowledge of…

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods…

The study of physical adversarial patches is crucial for identifying vulnerabilities in AI-based recognition systems and developing more robust deep learning models. While recent research has focused on improving patch stealthiness for…

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…

In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their…