Search Results for author:
Found 17 papers, 6 papers with code
Exploring the Benefits of Visual Prompting in Differential Privacy
Visual Prompting (VP) is an emerging and powerful technique that allows sample-efficient adaptation to downstream tasks by engineering a well-trained frozen source model.
Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise
Recently, quantum classifiers have been known to be vulnerable to adversarial attacks, where quantum classifiers are fooled by imperceptible noises to have misclassification.
DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis
Despite an increased demand for valuable data, the privacy concerns associated with sensitive datasets present a barrier to data sharing.
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations
Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, and adversarial attacks.
Catastrophic Data Leakage in Vertical Federated Learning
We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE).
Meta Adversarial Perturbations
A plethora of attack methods have been proposed to generate adversarial examples, among which the iterative methods have been demonstrated the ability to find a strong attack.
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE).
Real-World Adversarial Examples involving Makeup Application
The Cycle-GAN is used to generate adversarial makeup, and the architecture of the victimized classifier is VGG 16.
Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
However, the sensitive information in the datasets discourages data owners from releasing these datasets.
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations
Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, and adversarial attacks.
Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning
In this paper, we propose a framework of generating adversarial examples for unsupervised models and demonstrate novel applications to data augmentation.
Non-Singular Adversarial Robustness of Neural Networks
In this paper, we formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
Detecting Deepfake-Forged Contents with Separable Convolutional Neural Network and Image Segmentation
Deepfake can result in an erosion of public trust in digital images and videos, which has far-reaching effects on political and social stability.
Locally Differentially Private Minimum Finding
Instead of considering the worst case, we aim to construct a private mechanism whose error rate is adaptive to the easiness of estimation of the minimum.
On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces
Recent studies have found that deep learning systems are vulnerable to adversarial examples; e. g., visually unrecognizable adversarial images can easily be crafted to result in misclassification.
On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples
In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and security.
On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples
Understanding and characterizing the subspaces of adversarial examples aid in studying the robustness of deep neural networks (DNNs) to adversarial perturbations.
