2 papers
cs.CV2024
Twin Trigger Generative Networks for Backdoor Attacks against Object Detection
Zhiying Li, Zhi Liu, Guanggang Geng +4
Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained…
cs.CR2024
Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
Zhiying Li, Zhi Liu, Dongjie Liu +6
Backdoor watermarking has emerged as the predominant approach for protecting public datasets, enabling dataset ownership verification (DOV) through embedded triggers that induce pr…