Diffusion models for imperceptible and transferable adversarial attack
Many existing adversarial attacks generate-norm perturbations on image RGB space.
Despite some achievements in transferability and attack success rate, the crafted adversarial …
Despite some achievements in transferability and attack success rate, the crafted adversarial …
A comprehensive study on the robustness of deep learning-based image classification and object detection in remote sensing: Surveying and benchmarking
Deep neural networks (DNNs) have found widespread applications in interpreting remote
sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are …
sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are …
On the design fundamentals of diffusion models: A survey
Diffusion models are generative models, which gradually add and remove noise to learn the
underlying distribution of training data for data generation. The components of diffusion …
underlying distribution of training data for data generation. The components of diffusion …
Accelerated optimization in deep learning with a proportional-integral-derivative controller
High-performance optimization algorithms are essential in deep learning. However,
understanding the behavior of optimization (ie, learning process) remains challenging due …
understanding the behavior of optimization (ie, learning process) remains challenging due …
Diffattack: Evasion attacks against diffusion-based adversarial purification
Diffusion-based purification defenses leverage diffusion models to remove crafted
perturbations of adversarial examples and achieve state-of-the-art robustness. Recent …
perturbations of adversarial examples and achieve state-of-the-art robustness. Recent …
Extraction and recovery of spatio-temporal structure in latent dynamics alignment with diffusion models
In the field of behavior-related brain computation, it is necessary to align raw neural signals
against the drastic domain shift among them. A foundational framework within neuroscience …
against the drastic domain shift among them. A foundational framework within neuroscience …
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
Stable Diffusion has established itself as a foundation model in generative AI artistic
applications receiving widespread research and application. Some recent fine-tuning …
applications receiving widespread research and application. Some recent fine-tuning …
Sa-attack: Improving adversarial transferability of vision-language pre-training models via self-augmentation
Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples.
These adversarial examples present substantial security risks to VLP models, as they can …
These adversarial examples present substantial security risks to VLP models, as they can …
On the robustness of latent diffusion models
Latent diffusion models achieve state-of-the-art performance on a variety of generative tasks,
such as image synthesis and image editing. However, the robustness of latent diffusion …
such as image synthesis and image editing. However, the robustness of latent diffusion …
Toward effective protection against diffusion-based mimicry through score distillation
While generative diffusion models excel in producing high-quality images, they can also be
misused to mimic authorized images, posing a significant threat to AI systems. Efforts have …
misused to mimic authorized images, posing a significant threat to AI systems. Efforts have …