research
∙
07/19/2023
Backdoor Attack against Object Detection with Clean Annotation
Deep neural networks (DNNs) have shown unprecedented success in object d...
share
research
∙
05/03/2023
Backdoor Learning on Sequence to Sequence Models
Backdoor learning has become an emerging research area towards building ...
research
∙
05/03/2023
PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer
Recent studies show that prompt tuning can better leverage the power of ...
research
∙
02/03/2023
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks
In this work, besides improving prediction accuracy, we study whether pe...
research
∙
11/10/2022
MSDT: Masked Language Model Scoring Defense in Text Domain
Pre-trained language models allowed us to process downstream tasks with ...
research
∙
09/27/2022
Efficient Non-Parametric Optimizer Search for Diverse Tasks
Efficient and automated design of optimizers plays a crucial role in ful...
research
∙
07/20/2022
FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
Federated learning (FL) has recently attracted increasing attention from...
research
∙
11/18/2021
A Review of Adversarial Attack and Defense for Classification Methods
Despite the efficiency and scalability of machine learning systems, rece...
research
∙
08/18/2021
RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving
Predictor-based algorithms have achieved remarkable performance in the N...
research
∙
08/10/2021
Rethinking Architecture Selection in Differentiable NAS
Differentiable Neural Architecture Search is one of the most popular Neu...
research
∙
06/01/2021
Concurrent Adversarial Learning for Large-Batch Training
Large-batch training has become a commonly used technique when training ...
research
∙
12/22/2020
Self-Progressing Robust Training
Enhancing model robustness under new and even adversarial environments i...
research
∙
11/28/2020
Voting based ensemble improves robustness of defensive models
Developing robust models against adversarial perturbations has been an a...
research
∙
06/18/2020
DrNAS: Dirichlet Neural Architecture Search
This paper proposes a novel differentiable architecture search method by...
research
∙
02/17/2020
CAT: Customized Adversarial Training for Improved Robustness
Adversarial training has become one of the most effective methods for im...
research
∙
10/31/2019
Enhancing Certifiable Robustness via a Deep Model Ensemble
We propose an algorithm to enhance certified robustness of a deep model ...
research
∙
09/24/2019
Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
We study the most practical problem setup for evaluating adversarial rob...
research
∙
09/06/2019
Natural Adversarial Sentence Generation with Gradient-based Perturbation
This work proposes a novel algorithm to generate natural language advers...
research
∙
07/12/2018
Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
We study the problem of attacking a machine learning model in the hard-l...
research
∙
05/30/2018
Stochastic Zeroth-order Optimization via Variance Reduction method
Derivative-free optimization has become an important technique used in m...
research
∙
03/03/2018
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
Crafting adversarial examples has become an important technique to evalu...
research
∙
12/02/2017