Related papers: UIBDiffusion: Universal Imperceptible Backdoor Att…
Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor…
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…
Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses,…
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…
Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…
The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnerabilities of these solutions are underexplored. In this…
Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized…
Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…
Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…
Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many…
Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…
Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed…
Person Re-Identification (ReID) systems pose a significant security risk from backdoor attacks, allowing adversaries to evade tracking or impersonate others. Beyond recognizing this issue, we investigate how backdoor attacks can be deployed…
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,…
The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which are not only usually visually suspicious to human but also…
Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether…
Generative models have demonstrated revolutionary success in various visual creation tasks, but in the meantime, they have been exposed to the threat of leaking private information of their training data. Several membership inference…
Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…
Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms.…