Search Results for author:
Found 15 papers, 5 papers with code
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release.
Game-Theoretic Unlearnable Example Generator
Unlearnable example attacks are data poisoning attacks aiming to degrade the clean test accuracy of deep learning by adding imperceptible perturbations to the training samples, which can be formulated as a bi-level optimization problem.
Data-Dependent Stability Analysis of Adversarial Training
Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-based training algorithms.
Detection and Defense of Unlearnable Examples
Detectability of unlearnable examples with simple networks motivates us to design a novel defense method.
Restore Translation Using Equivariant Neural Networks
Invariance to spatial transformations such as translations and rotations is a desirable property and a basic design principle for classification neural networks.
Isometric 3D Adversarial Examples in the Physical World
For naturalness, we constrain the adversarial example to be $\epsilon$-isometric to the original one by adopting the Gaussian curvature as a surrogate metric guaranteed by a theoretical analysis.
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers.
Adversarial Parameter Attack on Deep Neural Networks
In this paper, a new parameter perturbation attack on DNNs, called adversarial parameter attack, is proposed, in which small perturbations to the parameters of the DNN are made such that the accuracy of the attacked DNN does not decrease much, but its robustness becomes much lower.
Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
The work is motivated by the fact that the bias part is a piecewise constant function with zero gradient and hence cannot be directly attacked by gradient-based methods to generate adversaries, such as FGSM.
A Robust Classification-autoencoder to Defend Outliers and Adversaries
In this paper, a robust classification-autoencoder (CAE) is proposed, which has strong ability to recognize outliers and defend adversaries.
A Generalization of the Concavity of Rényi Entropy Powe
Recently, Savar\'{e}-Toscani proved that the R\'{e}nyi entropy power of general probability densities solving the $p$-nonlinear heat equation in $\mathbb{R}^n$ is always a concave function of time, which extends Costa's concavity inequality for Shannon's entropy power to R\'{e}nyi entropies.
Information Theory Information Theory
Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
In this paper, we propose a general scheme to analyze the gradient vanishing phenomenon, also known as the barren plateau phenomenon, in training quantum neural networks with the ZX-calculus.
Improve the Robustness and Accuracy of Deep Neural Network with $L_{2,\infty}$ Normalization
A lower bound for the robustness measure is given in terms of the $L_{2,\infty}$ norm.
QDNN: DNN with Quantum Neural Network Layers
In this paper, we introduce a quantum extension of classical DNN, QDNN.
Quantum Algorithms for Boolean Equation Solving and Quantum Algebraic Attack on Cryptosystems
Decision of whether a Boolean equation system has a solution is an NPC problem and finding a solution is NP hard.
Quantum Physics Computational Complexity Cryptography and Security Symbolic Computation
