Trap and Replace: Defending Backdoor Attacks by Trapping Them into an
Easy-to-Replace Subnetwork

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

12 October 2022

Papers citing "Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork"

11 / 11 papers shown

Title
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Alvi Md Ishmam Christopher Thomas AAML 112 3 0 23 Nov 2024
Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers Zeyu Michael Li AAML 21 0 0 01 Oct 2024
Protecting against simultaneous data poisoning attacks Neel Alex Shoaib Ahmed Siddiqui Amartya Sanyal David M. Krueger AAML 40 1 0 23 Aug 2024
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks Changjiang Li Ren Pang Bochuan Cao Zhaohan Xi Jinghui Chen Shouling Ji Ting Wang AAML 32 6 0 14 Dec 2023
Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots Ruixiang Tang Jiayi Yuan Yiming Li Zirui Liu Rui Chen Xia Hu AAML 23 13 0 28 Oct 2023
Safe and Robust Watermark Injection with a Single OoD Image Shuyang Yu Junyuan Hong Haobo Zhang Haotao Wang Zhangyang Wang Jiayu Zhou WIGM 25 3 0 04 Sep 2023
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers Junyuan Hong Yi Zeng Shuyang Yu Lingjuan Lyu R. Jia Jiayu Zhou AAML 11 8 0 04 Jun 2023
Backdoor Defense via Adaptively Splitting Poisoned Dataset Kuofeng Gao Yang Bai Jindong Gu Yong-Liang Yang Shutao Xia AAML 13 1 0 23 Mar 2023
Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi Mengnan Du Xuansheng Wu Zihan Guan Jin Sun Ninghao Liu 32 26 0 21 Mar 2023
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free Tianlong Chen Zhenyu (Allen) Zhang Yihua Zhang Shiyu Chang Sijia Liu Zhangyang Wang AAML 44 25 0 24 May 2022
Poisoning the Unlabeled Dataset of Semi-Supervised Learning Nicholas Carlini AAML 139 68 0 04 May 2021