Related papers: Instant Adversarial Purification with Adversarial …
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.…
Diffusion Purification, purifying noised images with diffusion models, has been widely used for enhancing certified robustness via randomized smoothing. However, existing frameworks often grapple with the balance between efficiency and…
The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…
The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, privacy violations, and trust erosion in digital media.…
Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing samples from the BNN posterior using mini-batches. However,…
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…
Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based acceleration methods often face image quality degradation…
A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this limitation by…
Malicious applications of visual manipulation have raised serious threats to the security and reputation of users in many fields. To alleviate these issues, adversarial noise-based defenses have been enthusiastically studied in recent…
Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work…
Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training…
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…
3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in…
Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within…
In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i.e. transferring) knowledge from sensor data and enhancing low-resolution target detection. In unconstrained surveillance settings, sensor…
Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial…
Deep learning models for speech rely on large datasets, presenting computational challenges. Yet, performance hinges on training data size. Dataset Distillation (DD) aims to learn a smaller dataset without much performance degradation when…
Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adversarial…
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by…
Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle…