Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to t...
详细信息
Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to the black-box nature of deep learning. It is an urgent and challenging task to formally reason about the behaviors of RNNs. To this end, we first present an extension of linear-time temporal logic to reason about properties with respect to RNNs, such as local robustness, reachability, and some temporal properties. Based on the proposed logic, we formalize the verification obligation as a Hoare-like triple, from both qualitative and quantitative perspectives. The former concerns whether all the outputs resulting from the inputs fulfilling the pre-condition satisfy the post-condition, whereas the latter is to compute the probability that the post-condition is satisfied on the premise that the inputs fulfill the pre-condition. To tackle these problems, we develop a systematic verification framework, mainly based on polyhedron propagation, dimension-preserving abstraction, and the Monte Carlo sampling. We also implement our algorithm with a prototype tool and conduct experiments to demonstrate its feasibility and efficiency.
Federated Learning(FL),as an emergent paradigm in privacy-preserving machine learning,has garnered significant interest from scholars and engineers across both academic and industrial *** its innovative approach to mo...
详细信息
Federated Learning(FL),as an emergent paradigm in privacy-preserving machine learning,has garnered significant interest from scholars and engineers across both academic and industrial *** its innovative approach to model training across distributed networks,FL has its vulnerabilities;the centralized server-client architecture introduces risks of single-point ***,the integrity of the global model—a cornerstone of FL—is susceptible to compromise through poisoning attacks by malicious *** attacks and the potential for privacy leakage via inference starkly undermine FL’s foundational privacy and security *** these reasons,some participants unwilling use their private data to train a model,which is a bottleneck in the development and industrialization of federated *** technology,characterized by its decentralized ledger system,offers a compelling solution to these *** inherently prevents single-point failures and,through its incentive mechanisms,motivates participants to contribute computing ***,blockchain-based FL(BCFL)emerges as a natural progression to address FL’s *** study begins with concise introductions to federated learning and blockchain technologies,followed by a formal analysis of the specific problems that FL *** discusses the challenges of combining the two technologies and presents an overview of the latest cryptographic solutions that prevent privacy leakage during communication and incentives in *** addition,this research examines the use of BCFL in various fields,such as the Internet of Things and the Internet of ***,it assesses the effectiveness of these solutions.
Multi-exposure image fusion (MEF) involves combining images captured at different exposure levels to create a single, well-exposed fused image. MEF has a wide range of applications, including low light, low contrast, ...
详细信息
CXL, a new interconnect standard for cache-coherent memory sharing, is becoming a reality - but its security leaves something to be desired. Decentralized capabilities are flexible and resilient against malicious acto...
CXL, a new interconnect standard for cache-coherent memory sharing, is becoming a reality - but its security leaves something to be desired. Decentralized capabilities are flexible and resilient against malicious actors, and should be considered while CXL is under active development.
Deep learning methods have played a prominent role in the development of computer visualization in recent years. Hyperspectral imaging (HSI) is a popular analytical technique based on spectroscopy and visible imaging ...
详细信息
Lightweight video representation techniques have advanced significantly for simple activity recognition, but they still encounter several issues when applied to complex activity recognition: (i) The presence of numero...
详细信息
The combination of contextual side information and search is a powerful paradigm in the scope of artificial intelligence. The prior knowledge enables the identification of possible solutions but may be imperfect. Cont...
详细信息
The combination of contextual side information and search is a powerful paradigm in the scope of artificial intelligence. The prior knowledge enables the identification of possible solutions but may be imperfect. Contextual information can arise naturally, for example in game AI where prior knowledge is used to bias move decisions. In this work we investigate the problem of taking quantum advantage of contextual information, especially searching with prior knowledge. We propose a new generalization of Grover's search algorithm that achieves the optimal expected success probability of finding the solution if the number of queries is fixed. Experiments on small-scale quantum circuits verify the advantage of our algorithm. Since contextual information exists widely, our method has wide applications. We take game tree search as an example.
End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified *** methods heavily rely on region-of-interest(Rol)operations to extract local featur...
详细信息
End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified *** methods heavily rely on region-of-interest(Rol)operations to extract local features and complex post-processing steps to produce final *** address these limitations,we propose TextFormer,a query-based end-to-end text spotter with a transformer ***,using query embedding per text instance,TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multitask *** allows for mutual training and optimization of classification,segmentation and recognition branches,resulting in deeper feature sharing without sacrificing flexibility or ***,we design an adaptive global aggregation(AGG)module to transfer global features into sequential features for reading arbitrarilyshaped texts,which overcomes the suboptimization problem of Rol ***,potential corpus information is utilized from weak annotations to full labels through mixed supervision,further improving text detection and end-to-end text spotting *** experiments on various bilingual(i.e.,English and Chinese)benchmarks demonstrate the superiority of our *** on the TDA-ReCTS dataset,TextFormer surpasses the state-of-the-art method in terms of 1-NED by 13.2%.
Rapid urbanization has made road construction and maintenance imperative, but detecting road diseases has been time-consuming with limited accuracy. To overcome these challenges, we propose an efficient YOLOv7 road di...
详细信息
Low Earth Orbit (LEO) satellites play a crucial role in providing high-speed internet to remote areas and ensuring network resilience during outages. The design of efficient satellite constellations requires optimizin...
详细信息
暂无评论