相关论文: T2IShield: Defending Against Backdoors on Text-to-…

Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards have become the standard, relying on anonymized model outputs for fairness. In…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level…

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we…

Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on…

Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects, particularly the attributes characterizing them, remains a…

Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…

Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image.…

Diffusion-based text-to-image models have rapidly gained popularity for their ability to generate detailed and realistic images from textual descriptions. However, these models often reflect the biases present in their training data,…

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…

Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are facing security threats from backdoor attacks and can be…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

This paper presents Poisoning MorphNet, the first backdoor attack method on point clouds. Conventional adversarial attack takes place in the inference stage, often fooling a model by perturbing samples. In contrast, backdoor attack aims to…

With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly…

Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses…

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial…