Advanced artificial intelligence techniques, such as federated learning, has been applied to broad areas, e.g., image classification, speech recognition, smart city, and healthcare. Despite intensive research on existing schemes are vulnerable attacks can hardly meet the security requirements for real-world applications. The problem of designing a secure learning framework ensure correctness training procedure not sufficiently studied remains open. In this paper, we propose VFChain,...

The separated control and data planes in software-defined networking (SDN) with high programmability introduce a more flexible way to manage network traffic. However, SDN will experience long packet delay loss rate when the communication link between two is jammed by SDN-aimed DoS attacks massive table-miss packets. In this paper, we propose FloodDefender, an efficient protocol-independent defense framework for SDN/OpenFlow networks mitigate attacks. It stands controller platform other apps,...

The introduction of software-defined networking (SDN) has emerged as a new network paradigm for innovations. By decoupling the control plane from data in traditional networks, SDN provides high programmability to and manage networks. However, communication between two planes can be bottleneck whole network. SDN-aimed DoS attacks cause long packet delay loss rate by using massive table-miss packets jam links planes. To detect mitigate attacks, this paper presents FloodDefender, an efficient...

Many efforts have been devoted to the development of efficient Network Intrusion Detection System (NIDS) using machine learning approaches in Software-defined (SDN). Unfortunately, existing solutions failed detect real-time and zero-day attacks due their limited throughput prior knowledge-based detection. To this end, we propose Griffin, a NIDS that uses unsupervised expertise both known intrusion with high accuracy. Specifically, Griffin an feature extraction framework capture sequential...

SDN has enabled extensive network programmability and speedy innovations by decoupling the control plane from data plane. However, separation of two planes could also be a potential threat to whole network. Previous approaches pointed out that attackers can launch various attacks against SDN, such as DoS attacks, topology poisoning side-channel attacks. To address security issues, we present comprehensive study in propose FlowKeeper, common framework build robust different FlowKeeper...

Information about vehicle safety, such as the driving safety status and road index, is of great importance to protect humans support safe route planning. Despite some research on analysis, accuracy granularity assessment are both very limited. Also, problem precisely dynamically predicting throughout a city has not been sufficiently studied remains open. With proliferation sensor-equipped vehicles smart devices, huge amount mobile sensing data provides an opportunity conduct analysis. In...

Mining attacks allow attackers to gain an unfair share of the mining reward by deviating from honest strategy in Bitcoin system. Among most well-known are block withholding (BWH), fork after (FAW), and selfish mining. In this paper, we propose two new strategies: power adjusting bribery racing, introduce novel attacks, Power Adjusting Withholding (PAW) Bribery Selfish (BSM) adopting strategies. Both can increase attackers. Furthermore, show PAW avoid "miner's dilemma" BWH attacks. BSM...

With the advancement of medical science, implementation Electronic Medical Records (EMRs) for enhancing efficiency and reliability healthcare services has become a widespread phenomenon. However, EMRs are stored in hospitals institutions independently, leading to sharing challenges. Moreover, highly sensitive prone be tampered with abused, posing privacy security threats. To address aforementioned issues, we propose an Anti- Quantum Attribute-based Signature(AQ — ABS) Secure Sharing...

The Domain Name System (DNS) plays a crucial role in the Internet. However, it is vulnerable to many attacks such as cache poisoning attack and DDoS attack. Though some countermeasures have been proposed, they still limitations. In this paper, we propose B-DNS, blockchain-based domain name system, which can provide secure efficient DNS service. B-DNS fills up two shortcomings of current DNS, namely computation-heavy Proof-of-Work (PoW) protocol inefficient query, by building Proof-of-Stake...

With the advent of Big Data era, industry, business and academia have developed various data exchange schemes to make more economically beneficial. Unfortunately, most existing systems provide only one-time exchanges without ability track provenance transformations datasets. In addition, encrypt protect privacy, which hinders demanders from verifying correctness evaluating its value.To traceability privacy while ensuring fairness during exchanges, we design implement ZKDET, a traceable...

The Network Intrusion Detection Systems (NIDS) with machine learning in SDN become increasingly popular solutions. NIDS uses abnormal traffic detection to identify unknown network attacks. Most of today's systems are supposed continuously update the recognition model time based on features from newly collected packets accurately attack behaviors. However, those existing solutions always require a large number train offline. That means it is impossible detect emergence new cyber-attacks...

To reduce the transmission cost of blockchain confidential transactions, we propose SymmeProof, a novel communication efficient non-interactive zero-knowledge range proof protocol without trusted setup. We design and integrate two new techniques in namely vector compression inner-product proof. The proposed is able to log(n) for n-size vectors. converts relation into an form, which can further size with technique. Based on these techniques, SymmeProof eventually achieve log(n)-size be used...

Utilizing browsers to identify and track users has become a routine on the Web in recent years. It is easy for browser collect sensitive information construct comprehensive user profiles while are still unaware. As problem mentioned above, several anti-fingerprint mechanisms have been adopted protect privacy. However, our research finds novel method based localization fingerprints that may threaten The location fingerprint obtains response delay of data transmission over link between...

Unauthorized voice recording via smartphones can leak the talking content stealthily. This would be a serious security threat to those individuals, enterprises and government who need keep conversation confidential. Furthermore, due size miniaturization of smartphones, it is hard find covert from malicious attendees. Existing solutions usually jam with audible noise or electromagnetic emitting. However, will seriously interfere effect emitting limited by distance. In this paper, we propose...

Internet of Things (IoT) devices deployed in publicly accessible locations increasingly encounter security threats from device replacement and impersonation attacks. Unfortunately, the limited memory poor computing capability on such make solutions involving complex algorithms or enhanced authentication protocols untenable. To address this issue, identification technologies based traffic characteristics finger-printing have been proposed to prevent illegal intrusion impersonation. However,...

Since a growing number of malicious applications attempt to steal users’ private data by illegally invoking permissions, application stores have carried out many malware detection methods based on permissions. However, most them ignore specific permission combinations and categories that affect the accuracy. The features they extracted are neither representative enough distinguish benign applications. For these problems, an Android method sensitivity is proposed. First, for each kind...

Non-cryptographic mobile wireless device authentication based on channel signature has aroused extensive attention. This technology uses the device's physical characteristics to mark and verify its identity, can be used detect impersonation attacks information forgery attacks. Channel State Information (CSI) been generate fine-grained signatures. However, there are two sticking points in using CSI-based for association phase. The first is that state will change as moves, which means local...

In recent years, various sensors have been integrated into smartphones to sense the slight motions of human body. However, security researchers found that these can not only be used in motion detection, but also as side-channel reveal users' privacy data by inferring keystrokes. What is worse, defined W3C specifications, mobile web applications get sensor readings silently without permissions from users. Therefore, when cross-site scripting vulnerabilities are a application, attackers...

Smartphone sensors have been applied to record the movement of users for healthy use. However, motion sensor readings recorded by malicious applications can be utilized as a side-channel leak user privacy keystroke inference. Most existing approaches use time-domain statistical characteristics Their systems are poor show subtle changes in short time period, since time- domain features only reflect long-time interval. In this paper, we propose novel framework perform inference on smartphones....

Accurate digital maps play a crucial role in various location-based services and applications.However, store information is usually missing or outdated current maps.In this paper, we propose CrowdGIS, an automatic selfupdating system for that leverages street views sensing data crowdsourced from mobile users.We first develop new weighted artificial neural network to learn the underlying relationship between estimated positions real localize user's shooting positions.Then, novel text...

The advancement of Internet Medical Things (IoMT) leading to the proliferation electronic healthcare scenarios, with an expanding trend hospitals and organizations employing Electronic Records (EMRs) uploading cloud for sharing. However, security challenges exist during generation medical records, such as record tampering, key attacks, etc., which will become maximum bottleneck restricting development e-Health scenarios in near future. Some scholars consider digital signature techniques,...

With the development of sensing technology, smartphones can provide various kinds data, including inertial WiFi depth and images. These data make it possible to construct accurate indoor floor plans that are critical foundations flourishing location-based services for smartphone. However, even with popular crowdsourcing approach, wide construction has not yet be realized due intensive time consumption. In this paper, we utilize deep learning techniques build PlanSketcher, a system enables...

Energy saving solutions on smartphone devices can greatly extend a smartphone's lasting time. However, today's push services require keep-alive connections to notify users of incoming messages, which cause costly energy consuming and drain battery quickly in cellular communications. Most force smartphones frequently send heartbeat packets that create additional energy-consuming radio-tails. No previous work has addressed the high-energy consumption services. In this paper, we propose Single...