Related papers: Adversarial-Guided Diffusion for Multimodal LLM At…

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models'…

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used…

Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based…

Deep Learning (DL) is being applied in various domains, especially in safety-critical applications such as autonomous driving. Consequently, it is of great significance to ensure the robustness of these methods and thus counteract uncertain…

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Deep neural networks (DNNs) have shown vulnerability to adversarial attacks, i.e., carefully perturbed inputs designed to mislead the network at inference time. Recently introduced localized attacks, Localized and Visible Adversarial Noise…

Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this paper, we propose a new GAN variant called Mixture Density…

Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches…

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they…

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

Adversarial samples exploit irregularities in the manifold `learned' by deep learning models to cause misclassifications. The study of these adversarial samples provides insight into the features a model uses to classify inputs, which can…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…

Black-box adversarial attacks remain challenging due to limited access to model internals. Existing methods often depend on specific network architectures or require numerous queries, resulting in limited cross-architecture transferability…

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional context modeling. Yet their security implications,…

Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…

Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…

Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. However, their robustness against adversarial attacks has not…

While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection…