1

Visual Differential Signal Processing for Generative Image Editing

Deep generative models, particularly Generative Adversarial Networks (GANs), have made significant strides in the fields of image generation and manipulation. However, current image processing methods face two critical challenges: insufficient …

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

The advancement of diffusion models has enhanced the realism of AI-generated content but also raised concerns about misuse, necessitating robust copyright protection and tampering localization. Although recent methods have made progress toward …

Robustness Feature Adapter for Efficient Adversarial Training

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone models. AT is …

Influence-Guided Diffusion for Dataset Distillation

Dataset distillation aims to streamline the training process by creating a compact yet effective dataset for a much larger original dataset. However, existing methods often struggle with distilling large, high-resolution datasets due to prohibitive …

When Evolution Strategy Meets Language Models Tuning

Supervised Fine-tuning has been pivotal in training autoregressive language models, yet it introduces exposure bias. To mitigate this, Post Fine-tuning, including on-policy and off-policy methods, has emerged as a solution to enhance models further. …

Federated Learning with Hybrid Knowledge Distillations on Long-Tailed Heterogeneous Client Data

Federated learning (FL) has a great potential in large-scale machine learning applications by training a global model over distributed client data. However, FL deployed in real-world applications often incur collaboration bias and unstable …

Deep Ensemble Robustness by Adaptive Sampling in Dropout-Based Simultaneous Training

Recent studies show that an ensemble of deep networks can have better adversarial robustness by increasing the learning diversity of base models to limit adversarial transferability. However, existing schemes mostly rely on a second-order method for …

Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation

Distilled student models in teacher-student architectures are widely considered for computational-effective deployment in real-time applications and edge devices. However, there is a higher risk of student models to encounter adversarial attacks at …

Disentanglement of Deep Features for Adversarial Face Detection

Existing adversarial face detectors are mostly developed against specific types of attacks, and limited by their generalizability especially in adversarial settings. In this paper, we propose a new detection strategy based on a dual-classifier driven …

Individual Property Inference Over Collaborative Learning in Deep Feature Space

Collaborative learning is used in multi-media applications to distribute computing tasks and data storage over multiple sites. Recent studies found that private data information can be derived from model updates between the server and clients. Yet, …