Cloud computing and edge computing technologies offer effective solutions to the substantial storage and computational demands resulting from the rapid increase in edge network traffic. However, data outsourcing may lead to potential leakage of users’ sensitive information due to the limited trustworthiness of cloud and edge systems, allowing malicious users to conspire with these systems to access private data stored in the cloud. To mitigate security risks associated with collusion attacks on existing ciphertext search protocols, we propose a data security search protocol that is resistant to collusion in cloud-edge-end collaboration. This protocol enables fine-grained search of ciphertexts in the cloud while providing protection against collusion attacks. Furthermore, we have conducted formal methods analysis and verification of the protocol, demonstrating its alignment with its intended purpose.

Tumor cell detection plays a vital role in immunohistochemistry (IHC) quantitative analysis. While recent remarkable developments in fully-supervised deep learning have greatly contributed to the efficiency of this task, the necessity for manually annotating all cells of specific detection types remains impractical. Obviously, if we directly use full supervision to train these datasets, it can cause error in loss calculation due to the misclassification of unannotated cells as background. To address this issue, we observe that although some cells are omitted during the annotation process, these unannotated cells have a significant feature similarity with the annotated ones. Leveraging this characteristic, we propose a novel calibrated loss named Semantic Energy Loss (SEL). Specifically, our SEL automatically adjusts the loss to be lower for unannotated regions with similar semantic to the labeled ones, while penalizing regions with lager semantic difference. Besides, to prevent all regions from having similar semantics during training, we propose Stretched Feature Loss (SFL) that widen the semantic distance. We evaluate our method on two different IHC datasets and achieve significant performance improvements in both sparse and exhaustive annotation scenarios. Furthermore, we also validate that our method holds significant potential for detecting multiple types of cells. Our code is available at here.