Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection

8 August 2023

Papers citing "Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection"

5 / 5 papers shown

Title
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic Hang Wang Zhen Xiang David J. Miller G. Kesidis AAML 85 43 0 13 May 2022
Adversarial Unlearning of Backdoors via Implicit Hypergradient Yi Zeng Si-An Chen Won Park Z. Morley Mao Ming Jin R. Jia AAML 125 176 0 07 Oct 2021
Input-Aware Dynamic Backdoor Attack A. Nguyen Anh Tran AAML 74 431 0 16 Oct 2020
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems Wenbo Guo Lun Wang Masashi Sugiyama Min Du Basel Alomair 71 229 0 02 Aug 2019
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xinyun Chen Chang-rui Liu Yue Liu Kimberly Lu Basel Alomair AAML SILM 143 1,840 0 15 Dec 2017