Related papers: Backdoor Defense in Diffusion Models via Spatial A…

Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright…

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit…

Gaze estimation models are widely used in applications such as driver attention monitoring and human-computer interaction. While many methods for gaze estimation exist, they rely heavily on data-hungry deep learning to achieve high…

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Vision Transformers (ViTs) have become popular in computer vision tasks. Backdoor attacks, which trigger undesirable behaviours in models during inference, threaten ViTs' performance, particularly in security-sensitive tasks. Although…

Although diffusion-based techniques have shown remarkable success in image generation and editing tasks, their abuse can lead to severe negative social impacts. Recently, some works have been proposed to provide defense against the abuse of…

Many existing adversarial attacks generate $L_p$-norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards…

Text-to-image diffusion models can generate realistic images based on textual inputs, enabling users to convey their opinions visually through language. Meanwhile, within language, emotion plays a crucial role in expressing personal…

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,…

Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within…

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

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…

As a novel privacy-preserving paradigm aimed at reducing client computational costs and achieving data utility, split learning has garnered extensive attention and proliferated widespread applications across various fields, including smart…

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…

Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are…

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…

Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to…

Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright…