Search Results for author:
Found 24 papers, 15 papers with code
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected.
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive training information.
On the Generalization Ability of Unsupervised Pretraining
Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization.
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard.
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
To ensure that the prompts do not leak private information, we introduce the first private prompt generation mechanism, by a differentially-private (DP) ensemble of in-context learning with private demonstrations.
Understanding Deep Gradient Leakage via Inversion Influence Functions
Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors.
Safe and Robust Watermark Injection with a Single OoD Image
Training a high-performance deep neural network requires large amounts of data and computational resources.
FedNoisy: Federated Noisy Label Learning Benchmark
Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients.
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model.
Backdoor Defense for Data-Free Distillation with Poisoned Teachers
Data-free Knowledge Distillation
On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space
Recent studies demonstrated that the adversarially robust learning under $\ell_\infty$ attack is harder to generalize to different domains than standard domain adaptation.
A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection
Developing a mechanism for battling financial crimes is an impending task that requires in-depth collaboration from multiple institutions, and yet such collaboration imposed significant technical challenges due to the privacy and security requirements of distributed financial data.
MECTA: Memory-Economic Continual Test-Time Model Adaptation
The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory.
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection
We propose to take advantage of such heterogeneity and turn the curse into a blessing that facilitates OoD detection in FL.
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork
As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples.
How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts
Increasing concerns have been raised on deep learning fairness in recent years.
Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization
In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness.
Equalized Robustness: Towards Sustainable Fairness Under Distributional Shifts
In this paper, we first propose a new fairness goal, termed Equalized Robustness (ER), to impose fair model robustness against unseen distribution shifts across majority and minority groups.
Federated Adversarial Debiasing for Fair and Transferable Representations
While adversarial learning is commonly used in centralized learning for mitigating bias, there are significant barriers when extending it to the federated framework.
Federated Robustness Propagation: Sharing Robustness in Heterogeneous Federated Learning
In this paper, we study a novel FL strategy: propagating adversarial robustness from rich-resource users that can afford AT, to those with poor resources that cannot afford it, during federated learning.
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data.
Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent
In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
On Dynamic Noise Influence in Differential Private Learning
In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
Disturbance Grassmann Kernels for Subspace-Based Learning
In this paper, we focus on subspace-based learning problems, where data elements are linear subspaces instead of vectors.
