Search Results for author:
Found 20 papers, 4 papers with code
Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts.
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
The existence of adversarial attacks on machine learning models imperceptible to a human is still quite a mystery from a theoretical perspective.
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
Benefits of Transformer: In-Context Learning in Linear Regression Tasks with Unstructured Data
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage.
Superiority of Multi-Head Attention in In-Context Linear Regression
We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks.
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models.
Exploring Memorization in Fine-tuned Language Models
In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks.
FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Text-to-image generative models based on latent diffusion models (LDM) have demonstrated their outstanding ability in generating high-quality and high-resolution images according to language prompt.
Adversarial Training with Generated Data in High-Dimensional Regression: An Asymptotic Study
In recent years, studies such as \cite{carmon2019unlabeled, gowal2021improving, xing2022artificial} have demonstrated that incorporating additional real or generated data with pseudo-labels can enhance adversarial training through a two-stage training approach.
DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
By detecting the watermark from generated images, copyright infringement can be exposed with evidence.
Benefit of Interpolation in Nearest Neighbor Algorithms
In some studies \citep[e. g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero.
Unlabeled Data Help: Minimax Analysis and Adversarial Robustness
The recent proposed self-supervised learning (SSL) approaches successfully demonstrate the great potential of supplementing learning algorithms with additional unlabeled data.
On the Algorithmic Stability of Adversarial Training
In contrast, this paper studies the algorithmic stability of a generic adversarial training algorithm, which can further help to establish an upper bound for generalization error.
Adversarially Robust Estimate and Risk Analysis in Linear Regression
Further, we reveal an explicit connection of adversarial and standard estimates, and propose a straightforward two-stage adversarial learning framework, which facilitates to utilize model structure information to improve adversarial robustness.
On the Generalization Properties of Adversarial Training
Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed.
Directional Pruning of Deep Neural Networks
In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which searches for a sparse minimizer in or close to that flat region.
FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net
In this paper, we present a generic deep convolutional neural network (DCNN) for multi-class image segmentation.
Predictive Power of Nearest Neighbors Algorithm under Random Perturbation
We consider a data corruption scenario in the classical $k$ Nearest Neighbors ($k$-NN) algorithm, that is, the testing data are randomly perturbed.
Benefit of Interpolation in Nearest Neighbor Algorithms
The over-parameterized models attract much attention in the era of data science and deep learning.
Statistical Optimality of Interpolated Nearest Neighbor Algorithms
In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important.
