Search Results for author:
Found 14 papers, 4 papers with code
Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks.
Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection
Finally, we provide evidence of the potential applicability of our hypothesis in another DGM, PixelCNN++.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Frequency-aware GAN for Adversarial Manipulation Generation
We observe that existing spatial attacks cause large degradation in image quality and find the loss of high-frequency detailed components might be its major reason.
Scaling Private Deep Learning with Low-Rank and Sparse Gradients
Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration scales with model dimension, hindering the learning capability significantly.
Shuffle Gaussian Mechanism for Differential Privacy
We study Gaussian mechanism in the shuffle model of differential privacy (DP).
Privacy Amplification via Shuffled Check-Ins
We study a protocol for distributed computation called shuffled check-in, which achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler.
Network Shuffling: Privacy Amplification via Random Walks
However, introducing a centralized entity to the originally local privacy model loses some appeals of not having any centralized entity as in local differential privacy.
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
We propose a new framework of synthesizing data using deep generative models in a differentially private manner.
FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries
We investigate if one can leak or infer such private information without interacting with the teacher model directly.
P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee.
Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints.
Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
In this paper, we demonstrate that the node classifier can be deceived with high-confidence by poisoning just a single node even two-hops or more far from the target.
Locally Private Distributed Reinforcement Learning
To the best of our knowledge, this is the first work that actualizes distributed reinforcement learning under LDP.
Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples
Lipschitz margin training (LMT) is a scalable certified defense, but it can also only achieve small robustness due to over-regularization.
