Related papers: Invisible Backdoor Attacks on Diffusion Models

With the rapid advancement of diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target content using only 3 to 5 training images. More recently,…

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

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…

Diffusion models (DMs) have emerged as a promising approach for behavior cloning (BC). Diffusion policies (DP) based on DMs have elevated BC performance to new heights, demonstrating robust efficacy across diverse tasks, coupled with their…

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In these applications, conditional diffusion models incorporate…

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results,…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Suspect face generation remains a technical challenge in crime investigations. Traditional sketch-drawing workflows suffer from low efficiency and quality, while diffusion-based approaches still face intrinsic limitations on conditional…

Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks,…

Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees, thus making it hard to be applied for safety-critical applications. To address these challenges, we propose a new method,…

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…

In recent years, the neural network backdoor hidden in the parameters of the federated learning model has been proved to have great security risks. Considering the characteristics of trigger generation, data poisoning and model training in…

Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency and creativity. In this paper, we focus on diffusion…

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…