activity
20192023
most citedRethinking the Trigger of Backdoor Attack

97 citations · 307 across the 22 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.SD2022

A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4

Yiming Li, Zhifang Guo, Zhirong Ye +6

In this paper, we describe in detail our system for DCASE 2022 Task4. The system combines two considerably different models: an end-to-end Sound Event Detection Transformer (SEDT)…

cs.CR2022★ 26 cited

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

Yiming Li, Yang Bai, Yong Jiang +3

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets,…

cs.CR2022★ 2 cited

Black-box Dataset Ownership Verification via Backdoor Watermarking

Yiming Li, Mingyan Zhu, Xue Yang +3

Deep learning, especially deep neural networks (DNNs), has been widely and successfully adopted in many critical applications for its high effectiveness and efficiency. The rapid d…

cs.CR2022★ 42 cited

Backdoor Defense via Decoupling the Training Process

Kunzhe Huang, Yiming Li, Baoyuan Wu +2

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few trainin…

cs.CV2022★ 21 cited

Few-Shot Backdoor Attacks on Visual Object Tracking

Yiming Li, Haoxiang Zhong, Xingjun Ma +2

Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems. In current practice, third-p…