Biblio

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original audio signals by applying small time offsets and various types of distortions, such as background noise and room/microphone impulse responses. In the segment-level search task, where the conventional audio fingerprinting systems used to fail, our system using 10x smaller storage has shown promising results. Our code and dataset are available at https://mimbres.github.io/neural-audio-fp/.

Evolutionary computation (EC) is a kind of advanced computational intelligence (CI) algorithm and advanced artificial intelligence (AI) algorithm. EC algorithms have been widely studied for solving optimization and scheduling problems in various real-world applications, which act as one of the Big Three in CI and AI, together with fuzzy systems and neural networks. Even though EC has been fast developed in recent years, there is an assumption that the algorithm designer can obtain the objective function of the optimization problem so that they can calculate the fitness values of the individuals to follow the “survival of the fittest” principle in natural selection. However, in a real-world application scenario, there is a kind of problem that the objective function is privacy so that the algorithm designer can not obtain the fitness values of the individuals directly. This is the privacy-preserving optimization problem (PPOP) where the assumption of available objective function does not check out. How to solve the PPOP is a new emerging frontier with seldom study but is also a challenging research topic in the EC community. This paper proposes a rank-based cryptographic function (RCF) to protect the fitness value information. Especially, the RCF is adopted by the algorithm user to encrypt the fitness values of all the individuals as rank so that the algorithm designer does not know the exact fitness information but only the rank information. Nevertheless, the RCF can protect the privacy of the algorithm user but still can provide sufficient information to the algorithm designer to drive the EC algorithm. We have applied the RCF privacy-preserving method to two typical EC algorithms including particle swarm optimization (PSO) and differential evolution (DE). Experimental results show that the RCF-based privacy-preserving PSO and DE can solve the PPOP without performance loss.

The design of public-key cryptography algorithm based on LWE hard problem is a hot topic in the field of post-quantum cryptography. In this paper, we design a new homomorphic encryption algorithm based on LWE problem. Firstly, to solve the problem that the existing encryption algorithms can only encrypt a single 0 or 1 bit, a new encryption algorithm based on LWE over integer is proposed, and its correctness and security are proved by theoretical analysis. Secondly, an additive homomorphism algorithm is constructed based on the algorithm, and the correctness of the algorithm is proved. The homomorphism algorithm can carry out multi-level homomorphism addition under certain parameters. Finally, the public key cryptography algorithm and homomorphic encryption algorithm are simulated through experiments, which verifies the correctness of the algorithm again, and compares the efficiency of the algorithm with existing algorithms. The experimental data shows that the algorithm has certain efficiency advantages.

Modern IoT infrastructure consists of different sub-systems, devices, applications, platforms, varied connectivity protocols with distinct operating environments scattered across different subsystems within the whole network. Each of these subsystems of the global system has its peculiar computational and security challenges. A security loophole in one subsystem has a directly negative impact on the security of the whole system. The nature and intensity of recent cyber-attacks within IoT networks have increased in recent times. Blockchain technology promises several security benefits including a decentralized authentication mechanism that addresses almost readily the challenges with a centralized authentication mechanism that has the challenges of introducing a single point of failure that affects data and system availability anytime such systems are compromised. The different design specifications and the unique functional requirements for most IoT devices require a strong yet universal authentication mechanism for multimedia data that assures an additional security layer to IoT data. In this paper, the authors propose a decentralized authentication to validate data integrity at the IoT node level. The proposed mechanism guarantees integrity, privacy, and availability of IoT node data.

With the rapid development of power Internet of Things (IoT), the ubiquitous edge agents are frequently exposed in a risky environment, where the white-box attacker could steal all the internal information by full observation of dynamic execution of the cryptographic software. In this situation, a new table-based white-box cryptography implementation of SM4 algorithm is proposed to prevent the attacker from extracting the secret key, which hides the encryption and decryption process in obfuscated lookup tables. Aiming to improve the diversity and ambiguity of the lookup tables as well as resist different types of white-box attacks, the random bijective nonlinear mappings are applied as scrambling encodings of the lookup tables. Moreover, in order to make our implementation more practical in the resource-constrained edge IoT agent, elaborate design is proposed to make some tables reusability, leading to less memory occupation while guaranteeing the security. The validity and security of the proposed implementation will be illustrated through several evaluation indicators.

Underwater Wireless Sensor Networks (UWSN) has vast application areas. Due to the unprotected nature, underwater security is a prime concern. UWSN becomes vulnerable to different attacks due to malicious nodes. Sybil attack is one of the major attacks in UWSN. Most of the proposed security methods are based on encryption and decryption which consumes resources of the sensor nodes. In this paper, a simple authentication mechanism is proposed for securing the UWSN from the Sybil attack. As the nodes have very less computation power and energy resources so this work is not followed any kind of encryption and decryption technique. An authentication process is designed in such a way that node engaged in communication authenticate neighboring nodes by node ID and the data stored in the cluster head. This work is also addressed sensor node compromisation issue through Hierarchical Fuzzy System (HFS) based trust management model. The trust management model has been simulated in Xfuzzy-3.5. After the simulation conducted, the proposed trust management mechanism depicts significant performance on detecting compromised nodes.

Many critical industrial control systems integrate a mixture of state-of-the-art and legacy equipment. Legacy installations lack advanced, and often even basic security features, risking entire system security. Existing research primarily focuses on the development of secure protocols for emerging devices or protocol translation proxies for legacy equipment. However, a robust security framework not only needs encryption but also mechanisms to prevent reconnaissance and unauthorized access to industrial devices. This paper proposes a novel Edge Security Gateway (ESG) that provides both, communication and endpoint security. The ESG is based on double ratchet algorithm and encrypts every message with a different key. It manages the ongoing renewal of short-lived session keys and provides localized firewall protection to individual devices. The ESG is easily customizable for a wide range of industrial application. As a use case, this paper presents the design and validation for synchrophasor technology in smart grid. The ESG effectiveness is practically validated in detecting reconnaissance, manipulation, replay, and command injection attacks due to its perfect forward and backward secrecy properties.

State estimation algorithm ensures an effective realtime monitoring of the modern smart grid leading to an accurate determination of the current operating states. Recently, a new genre of data integrity attacks namely false data injection attack (FDIA) has shown its deleterious effects by bypassing the traditional bad data detection technique. Modern grid operators must detect the presence of such attacks in the raw field measurements to guarantee a safe and reliable operation of the grid. State forecasting based FDIA identification schemes have recently shown its efficacy by determining the deviation of the estimated states due to an attack. This work emphasizes on a scalable deep learning state forecasting model which can accurately determine the presence of FDIA in real-time. An optimal set of hyper-parameters of the proposed architecture leads to an effective forecasting of the operating states with minimal error. A diligent comparison between other state of the art forecasting strategies have promoted the effectiveness of the proposed neural network. A comprehensive analysis on the IEEE 14 bus test bench effectively promotes the proposed real-time attack identification strategy.

Security is the main concern for wireless sensor nodes and exposed against malicious attacks. To secure the communication between sensor nodes several key managing arrangements are already implemented. The key managing method for any protected application must minimally deliver safety facilities such as truthfulness. Diffie–Hellman key exchange in the absence of authentication is exposed to MITM (man-in-the-middle) attacks due to which the attacker node can easily interrupt the communication, by appearing as a valid node in the network. In wireless sensor networks, single path routing is very common but it suffers with the two problems i:e link failure which results in data loss and if any node in single path is compromised, there is no alternative to send the data to the destination securely. To overcome this problem, multipath routing protocol is used which provides both availability and consistency of data. AOMDV (Ad-hoc On-demand Multipath Distance Vector Routing Protocol) is used in a proposed algorithm which provides alternative paths to reach the data packets to the destination. This paper presents an algorithm DH-SAM (Diffie-Hellman- Sybil Attack Mitigation) to spot and mitigate Sybil nodes and make the network trusted with the objective of solving the issue of MITM attack in the network. After node authentication, secure keys are established between two communicating nodes for data transmission using the Diffie-Hellman algorithm. Performance evaluation of DH-SAM is done by using different metrics such as detection rate, PDR, throughput, and average end to end (AE2E) delay.

This paper presents the results of a multifaceted study of the behavior of a novel hydrokinetic energy harvester that utilizes vertical oscillations. Unlike traditional rotating turbines used in hydrokinetic energy, this particular device utilizes the fluid structure interactions of vortex-induced-vibration and gallop. Due to the unique characteristics of this vertical motion, a thorough examination of the proposed system was conducted via a three-pronged approach of simulation, emulation, and field testing. Using a permanent magnet synchronous generator as the electrical power generation source, an electrical power conversion system was simulated, emulated, and tested to achieve appropriate power smoothing for use in microgrid systems present in many Alaskan rural locations.

Most of the studies of the existing object detection models are studies to better detect the objects to be detected. The problem of false detection of objects that should not be detected is not considered. When an object detection model that does not take this problem into account is applied to an industrial field close to humans, false detection can lead to a dangerous situation that greatly interferes with human life. To solve this false detection problem, this paper proposes a method of fine-tuning the backbone neural network model of the object detection model using the Outlier Exposure method and applying the class-specific uncertainty constant to the confidence score to detect the object.

Addressing vulnerability propagation has become a major issue in software ecosystems. Existing approaches hold the promise of detecting widespread vulnerabilities but cannot be applied to verify effectively whether propagated vulnerable code still poses threats. We present OCTOPOCS, which uses a reformed Proof-of-Concept (PoC), to verify whether a vulnerability is propagated. Using context-aware taint analysis, OCTOPOCS extracts crash primitives (the parts used in the shared code area between the original vulnerable software and propagated software) from the original PoC. OCTOPOCS then utilizes directed symbolic execution to generate guiding inputs that direct the execution of the propagated software from the entry point to the shared code area. Thereafter, OCTOPOCS creates a new PoC by combining crash primitives and guiding inputs. It finally verifies the propagated vulnerability using the created PoC. We evaluated OCTOPOCS with 15 real-world C and C++ vulnerable software pairs, with results showing that OCTOPOCS successfully verified 14 propagated vulnerabilities.

The use of gamified learning platforms as a method of introducing cyber security education, training and awareness has risen greatly. With this rise, the availability of platforms to create, host or otherwise provide the challenges that make up the foundation of this education has also increased. In order to identify the best of these platforms, we need a method to compare their feature sets. In this paper, we compare related work on identifying the best platforms for a gamified cyber security learning platform as well as contemporary literature that describes the most needed feature sets for an ideal platform. We then use this to develop a metric for comparing these platforms, before then applying this metric to popular current platforms.

The electron mobility μ exhibits oscillatory behavior with gate electric field F in an asymmetrically doped double V-shaped AlxGa1-xAs quantum well field effect transistor structure. By changing F, single-double-single subband occupancy of the system is obtained. We show that μ oscillates within double subband occupancy as a function of F near resonance of subband states due to the relocation of subband wave functions between the wells through intersubband effects.

This paper studies event-triggered output-based security control of nonlinear system under deception attacks obeying a Bernoulli distribution. Firstly, to save system resources of a T-S fuzzy system, an output-based discrete event-triggered mechanism (ETM) is introduced, which excludes Zeno behavior absolutely. Secondly, a closed-loop T-S fuzzy system model is built, which integrates parameters of the nonlinear plant, the ETM, stochastic attacks, fuzzy dynamic output feedback controller and network-induced delays in a unified framework. Thirdly, sufficient conditions for asymptotic stability of the T-S fuzzy sys$łnot$tem are derived, and the design method of a fuzzy output-based security controller is presented. Finally, an example illustrates effectiveness of the proposed method.

In Mobile Ad-hoc Network based Internet of things (MANET-IoT), nodes are mobile, infrastructure less, managed and organized by themselves that have important role in many areas such as Mobile Computing, Military Sector, Sensor Networks Commercial Sector, medical etc. One major problem in MANET based IoT is security because nodes are mobile, having not any central administrator and are also not reliable. So, MANET-IoT is more defenseless to denial-of-service attacks for-example Blackhole, Wormhole, Gray-hole etc. To compare the performance of network under different attacks for checking which attack is more affecting the performance of network, we implemented Blackhole and Wormhole attack by modifying AODV routing protocol in NS-3. After preprocessing of data that is obtained by using Flow-monitor module, we calculated performance parameters such as Average Throughput, Average Packet Delivery Ratio, Average End to End Delay, Average Jitter-Sum and compared it with no. of nodes in MANET-IoT network. Throughput and goodput performance of each node in the network is also calculated by using Trace metric module and compared with each node in the network. This approach is also very helpful for further research in MANET-IoT Security.

In this paper, we propose a numerical simulation investigation of the wavelength division multiplexing mechanism between a chaotic secure channel and a traditional fiber channel using the advanced modulation method DP-16QAM at the bitrate of 80Gbps, the fiber length of 80 km and 100 GHz channel spacing in C-band. Our paper investigates correlation coefficients between the transmitter and also the receiver for two forms of communication channels. Our simulation results demonstrate that, in all cases, BER is always below 2.10-4 even when we have not used the forward-error-correction method. Besides, cross-interaction between the chaotic channel and also the non-chaotic channel is negligible showing a highly independent level between two channels.

Compressive Sensing (CS) is a promising investigation field in the communication signal processing domain. It offers an advantage of compression while sampling; hence, data redundancy is reduced and improves sampled data transmission. Due to the acquisition of compressed samples, Analog to Digital Conversions (ADCs) performance also improved at ultra-high frequency communication applications. Several reconstruction algorithms existed to reconstruct the original signal with these sub-Nyquist samples. Orthogonal Matching Pursuit (OMP) falls under the category of greedy algorithms considered in this work. We implemented a compressively sensed sampling procedure using a Random Demodulator Analog-to-Information Converter (RD-AIC). And for CS reconstruction, we have considered OMP and novel Incremental Gaussian Elimination (IGE) OMP algorithms to reconstruct the original signal. Performance comparison between OMP and IGE OMP presented.

In this paper, we propose a deep learning based detection for multiple input multiple output (MIMO) physical-layer network coding (DeepPNC) over two way relay channels (TWRC). In MIMO-PNC, the relay node receives the signals superimposed from the two end nodes. The relay node aims to obtain the network-coded (NC) form of the two end nodes' signals. By training suitable deep neural networks (DNNs) with a limited set of training samples. DeepPNC can extract the NC symbols from the superimposed signals received while the output of each layer in DNNs converges. Compared with the traditional detection algorithms, DeepPNC has higher mapping accuracy and does not require channel information. The simulation results show that the DNNs based DeepPNC can achieve significant gain over the DeepNC scheme and the other traditional schemes, especially when the channel matrix changes unexpectedly.

In protocol verification we observe a wide spectrum from fully automated methods to interactive theorem proving with proof assistants like Isabelle/HOL. The latter provide overwhelmingly high assurance of the correctness, which automated methods often cannot: due to their complexity, bugs in such automated verification tools are likely and thus the risk of erroneously verifying a flawed protocol is non-negligible. There are a few works that try to combine advantages from both ends of the spectrum: a high degree of automation and assurance. We present here a first step towards achieving this for a more challenging class of protocols, namely those that work with a mutable long-term state. To our knowledge this is the first approach that achieves fully automated verification of stateful protocols in an LCF-style theorem prover. The approach also includes a simple user-friendly transaction-based protocol specification language embedded into Isabelle, and can also leverage a number of existing results such as soundness of a typed model

Non-orthogonal multiple access (NOMA) is emerging as a popular radio access technique to serve multiple users under the same resource block to improve spectral efficiency in 5G and 6G communication. But the resource sharing in NOMA causes concerns on data security. Since power domain NOMA exploits the difference in channel properties for bandwidth-efficient communication, it is feasible to ensure data confidentiality in NOMA communication through physical layer security techniques. In this work, we propose to ensure resistance against internal eavesdropping in NOMA communication through a secret key derived from channel randomness. A unique secret key is derived from the channel of each NOMA user; which is used to randomize the data of the respective user before superposition coding (SC) to prevent internal eavesdropping. The simulation results show that the proposed system provides very good security against internal eavesdropping in NOMA.

Physical-layer security is a new paradigm that offers data protection against eavesdropping in wireless 5G networks. In this context, the Gaussian channel is a typical model that captures the practical aspects of confidentially transmitting a message through the wireless medium. In this paper, we consider the peculiar case of transmitting a message through a wireless, state-dependent channel which is prone to eavesdropping, where the state knowledge is non-causally known and shared between the sender and the eavesdropper. We show that a novel structured coding scheme, which combines random coding arguments and the dirty-paper coding technique, achieves the fundamental limit of secure and reliable communication for the considered model.

Among many application domains of machine learning in real-world settings, cyber security can benefit from more automated techniques to combat sophisticated adversaries. Modern network intrusion detection systems leverage machine learning models on network logs to proactively detect cyber attacks. However, the risk of adversarial attacks against machine learning used in these cyber settings is not fully explored. In this paper, we investigate poisoning attacks at training time against machine learning models in constrained cyber environments such as network intrusion detection; we also explore mitigations of such attacks based on training data sanitization. We consider the setting of poisoning availability attacks, in which an attacker can insert a set of poisoned samples at training time with the goal of degrading the accuracy of the deployed model. We design a white-box, realizable poisoning attack that reduced the original model accuracy from 95% to less than 50 % by generating mislabeled samples in close vicinity of a selected subset of training points. We also propose a novel Nested Training method as a defense against these attacks. Our defense includes a diversified ensemble of classifiers, each trained on a different subset of the training set. We use the disagreement of the classifiers' predictions as a data sanitization method, and show that an ensemble of 10 SVM classifiers is resilient to a large fraction of poisoning samples, up to 30% of the training data.

Network function virtualization (NFV) simplies the coniguration and management of security services by migrating the network security functions from dedicated hardware devices to software middle-boxes that run on commodity servers. Under the paradigm of NFV, the service function chain (SFC) consisting of a series of ordered virtual network security functions is becoming a mainstream form to carry network security services. Allocating the underlying physical network resources to the demands of SFCs under given constraints over time is known as the SFC deployment problem. It is a crucial issue for infrastructure providers. However, SFC deployment is facing new challenges in trading off between pursuing the objective of a high revenue-to-cost ratio and making decisions in an online manner. In this paper, we investigate the use of reinforcement learning to guide online deployment decisions for SFC requests and propose a Policy network Assisted Monte Carlo Tree search approach named PACT to address the above challenge, aiming to maximize the average revenue-to-cost ratio. PACT combines the strengths of the policy network, which evaluates the placement potential of physical servers, and the Monte Carlo Tree Search, which is able to tackle problems with large state spaces. Extensive experimental results demonstrate that our PACT achieves the best performance and is superior to other algorithms by up to 30% and 23.8% on average revenue-to-cost ratio and acceptance rate, respectively.

To ensure the safe operation of power system, this paper studies two technologies of data encryption and digital signature, and designs a real-time data encryption system based on DES algorithm, which improves the security of data network communication. The real-time data encryption system of power system is optimized by the hybrid encryption system based on DES algorithm. The real-time data encryption of power system adopts triple DES algorithm, and double DES encryption algorithm of RSA algorithm to ensure the security of triple DES encryption key, which solves the problem of real-time data encryption management of power system. Java security packages are used to implement digital signatures that guarantee data integrity and non-repudiation. Experimental results show that the data encryption system is safe and effective.