Search Results for author:
Found 11 papers, 9 papers with code
DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection
Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i. e.}, increasing the amplitude of augmentation carefully to avoid degrading some data too much and doing harm to the model performance.
Improving Transferability of Adversarial Examples via Bayesian Attacks
Our ICLR work advocated for enhancing transferability in adversarial examples by incorporating a Bayesian formulation into model parameters, which effectively emulates the ensemble of infinitely many deep neural networks, while, in this paper, we introduce a novel extension by incorporating the Bayesian formulation into the model input as well, enabling the joint diversification of both the model input and model parameters.
Improving Adversarial Transferability via Intermediate-level Perturbation Decay
In particular, the proposed method, named intermediate-level perturbation decay (ILPD), encourages the intermediate-level perturbation to be in an effective adversarial direction and to possess a great magnitude simultaneously.
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
In this paper, by contrast, we opt for the diversity in substitute models and advocate to attack a Bayesian model for achieving desirable transferability.
Adversarial Contrastive Learning via Asymmetric InfoNCE
Contrastive learning (CL) has recently been applied to adversarial learning tasks.
Squeeze Training for Adversarial Robustness
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community.
An Intermediate-level Attack Framework on The Basis of Linear Regression
This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples.
On Steering Multi-Annotations per Sample for Multi-Task Learning
Despite the remarkable progress, the challenge of optimally learning different tasks simultaneously remains to be explored.
Backpropagating Linearly Improves Transferability of Adversarial Examples
The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community.
Practical No-box Adversarial Attacks against DNNs
We propose three mechanisms for training with a very small dataset (on the order of tens of examples) and find that prototypical reconstruction is the most effective.
Yet Another Intermediate-Level Attack
The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks.
