Hua Ma

Hua Ma, Shang Wang, Yansong Gao et al.

All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implications. This study introduces a new, simple, and general type of backdoor attack coined as the horizontal class backdoor (HCB) that trivially breaches the class dependence characteristic of the VCB, bringing a fresh perspective to the community. HCB is now activated when the trigger is presented together with an innocuous feature, regardless of class. For example, the facial recognition model misclassifies a person who wears sunglasses with a smiling innocuous feature into the targeted person, such as an administrator, regardless of which person. The key is that these innocuous features are horizontally shared among classes but are only exhibited by partial samples per class. Extensive experiments on attacking performance across various tasks, including MNIST, facial recognition, traffic sign recognition, object detection, and medical diagnosis, confirm the high efficiency and effectiveness of the HCB. We rigorously evaluated the evasiveness of the HCB against a series of eleven representative countermeasures, including Fine-Pruning (RAID 18'), STRIP (ACSAC 19'), Neural Cleanse (Oakland 19'), ABS (CCS 19'), Februus (ACSAC 20'), NAD (ICLR 21'), MNTD (Oakland 21'), SCAn (USENIX SEC 21'), MOTH (Oakland 22'), Beatrix (NDSS 23'), and MM-BD (Oakland 24'). None of these countermeasures prove robustness, even when employing a simplistic trigger, such as a small and static white-square patch.

Hua Ma, Ihor Smal, Joost Daemen et al.

Percutaneous coronary intervention (PCI) is typically performed with image guidance using X-ray angiograms in which coronary arteries are opacified with X-ray opaque contrast agents. Interventional cardiologists typically navigate instruments using non-contrast-enhanced fluoroscopic images, since higher use of contrast agents increases the risk of kidney failure. When using fluoroscopic images, the interventional cardiologist needs to rely on a mental anatomical reconstruction. This paper reports on the development of a novel dynamic coronary roadmapping approach for improving visual feedback and reducing contrast use during PCI. The approach compensates cardiac and respiratory induced vessel motion by ECG alignment and catheter tip tracking in X-ray fluoroscopy, respectively. In particular, for accurate and robust tracking of the catheter tip, we proposed a new deep learning based Bayesian filtering method that integrates the detection outcome of a convolutional neural network and the motion estimation between frames using a particle filtering framework. The proposed roadmapping and tracking approaches were validated on clinical X-ray images, achieving accurate performance on both catheter tip tracking and dynamic coronary roadmapping experiments. In addition, our approach runs in real-time on a computer with a single GPU and has the potential to be integrated into the clinical workflow of PCI procedures, providing cardiologists with visual guidance during interventions without the need of extra use of contrast agent.