ResearchTrend.AI
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning

What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning

Jonas Geiping
Liam H. Fowl
Gowthami Somepalli
Micah Goldblum
Michael Moeller
Tom Goldstein
ArXivPDFHTML

Papers citing "What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning"

4 / 4 papers shown
Title
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
Zhenxing Niu
Yuyao Sun
Qiguang Miao
Rong Jin
Gang Hua
AAML
21
6
0
28 May 2024
Projected Subnetworks Scale Adaptation
Projected Subnetworks Scale Adaptation
Siddhartha Datta
N. Shadbolt
VLM
CLL
16
0
0
27 Jan 2023
On the Effectiveness of Adversarial Training against Backdoor Attacks
On the Effectiveness of Adversarial Training against Backdoor Attacks
Yinghua Gao
Dongxian Wu
Jingfeng Zhang
Guanhao Gan
Shutao Xia
Gang Niu
Masashi Sugiyama
AAML
21
22
0
22 Feb 2022
On Evaluating Neural Network Backdoor Defenses
On Evaluating Neural Network Backdoor Defenses
A. Veldanda
S. Garg
AAML
16
8
0
23 Oct 2020