Related papers: Elijah: Eliminating Backdoors Injected in Diffusio…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Recently, the diffusion model has gained significant attention as one of the most successful image generation models, which can generate high-quality images by iteratively sampling noise. However, recent studies have shown that diffusion…
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…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…
Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest of the image. Although diffusion models have been shown to…
The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the…
Diffusion models (DMs) have demonstrated great potential in the field of adversarial robustness, where DM-based defense methods can achieve superior defense capability without adversarial training. However, they all require huge…
Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…
While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive…
Diffusion models have achieved remarkable success in imaging inverse problems owing to their powerful generative capabilities. However, existing approaches typically rely on models trained for specific degradation types, limiting their…
Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…
It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion…
Diffusion Models have emerged as powerful generative models for high-quality image synthesis, with many subsequent image editing techniques based on them. However, the ease of text-based image editing introduces significant risks, such as…
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…
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,…
Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…
The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial…
Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of these collected data…
Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…