Biblio

With 3.78 billion social media users worldwide in 2021 (48% of the human population), almost 3 billion images are shared daily. At the same time, a consistent evolution of smartphone cameras has led to a photography explosion with 85% of all new pictures being captured using smartphones. However, lately, there has been an increased discussion of privacy concerns when a person being photographed is unaware of the picture being taken or has reservations about the same being shared. These privacy violations are amplified for people with disabilities, who may find it challenging to raise dissent even if they are aware. Such unauthorized image captures may also be misused to gain sympathy by third-party organizations, leading to a privacy breach. Privacy for people with disabilities has so far received comparatively less attention from the AI community. This motivates us to work towards a solution to generate privacy-conscious cues for raising awareness in smartphone users of any sensitivity in their viewfinder content. To this end, we introduce PrivPAS (A real time Privacy-Preserving AI System) a novel framework to identify sensitive content. Additionally, we curate and annotate a dataset to identify and localize accessibility markers and classify whether an image is sensitive to a featured subject with a disability. We demonstrate that the proposed lightweight architecture, with a memory footprint of a mere 8.49MB, achieves a high mAP of 89.52% on resource-constrained devices. Furthermore, our pipeline, trained on face anonymized data. achieves an F1-score of 73.1%.

In recent years, artificial intelligence technology based on image data has been widely used in various industries. Rational analysis and mining of image data can not only promote the development of the technology field but also become a new engine to drive economic development. However, the privacy leakage problem has become more and more serious. To solve the privacy leakage problem of image data, this paper proposes the RDP-WGAN privacy protection framework, which deploys the Rényi differential privacy (RDP) protection techniques in the training process of generative adversarial networks to obtain a generative model with differential privacy. This generative model is used to generate an unlimited number of synthetic datasets to complete various data analysis tasks instead of sensitive datasets. Experimental results demonstrate that the RDP-WGAN privacy protection framework provides privacy protection for sensitive image datasets while ensuring the usefulness of the synthetic datasets.

To solve the current problem of scarce information security talents, this paper proposes to design a network information security attack and defense practical training platform based on ThinkPHP framework. It provides help for areas with limited resources and also offers a communication platform for the majority of information security enthusiasts and students. The platform is deployed using ThinkPHP, and in order to meet the personalized needs of the majority of users, support vector machine algorithms are added to the platform to provide a more convenient service for users.

GIS equipment is an important component of power system, and mechanical failure often occurs in the process of equipment operation. In order to realize GIS equipment mechanical fault intelligent detection, this paper presents a mechanical fault diagnosis model for GIS equipment based on cross-validation parameter optimization support vector machine (CV-SVM). Firstly, vibration experiment of isolating switch was carried out based on true 110 kV GIS vibration simulation experiment platform. Vibration signals were sampled under three conditions: normal, plum finger angle change fault, plum finger abrasion fault. Then, the c and G parameters of SVM are optimized by cross validation method and grid search method. A CV-SVM model for mechanical fault diagnosis was established. Finally, training and verification are carried out by using the training set and test set models in different states. The results show that the optimization of cross-validation parameters can effectively improve the accuracy of SVM classification model. It can realize the accurate identification of GIS equipment mechanical fault. This method has higher diagnostic efficiency and performance stability than traditional machine learning. This study can provide reference for on-line monitoring and intelligent fault diagnosis analysis of GIS equipment mechanical vibration.

Aiming at the single hopping strategy in the terminal information hopping active defense technology, a variety of heterogeneous hopping modes are introduced into the terminal information hopping system, the definition of the terminal information is expanded, and the adaptive adjustment of the hopping strategy is given. A network adversarial training simulation system is researched and designed, and related subsystems are discussed from the perspective of key technologies and their implementation, including interactive adversarial training simulation system, adversarial training simulation support software system, adversarial training simulation evaluation system and adversarial training Mock Repository. The system can provide a good environment for network confrontation theory research and network confrontation training simulation, which is of great significance.

Deep learning has been widely applied for jobs involving face inpainting, however, there are usually some problems, such as incoherent inpainting edges, lack of diversity of generated images and other problems. In order to get more feature information and improve the inpainting effect, we therefore propose a Generative Adversarial Network of Skip Connection (SCGAN), which connects the encoder layers and the decoder layers by skip connection in the generator. The coherence and consistency of the image inpainting edges are improved, and the finer features of the image inpainting are refined, simultaneously using the discriminator's local and global double discriminators model. We also employ WGAN-GP loss to enhance model stability during training, prevent model collapse, and increase the variety of inpainting face images. Finally, experiments on the CelebA dataset and the LFW dataset are performed, and the model's performance is assessed using the PSNR and SSIM indices. Our model's face image inpainting is more realistic and coherent than that of other models, and the model training is more reliable.

A recommender system aims to suggest the most relevant items to users based on their personal data. However, data privacy is a growing concern for anyone. Secure recommender system is a research direction to preserve user privacy while maintaining as high performance as possible. The most recent strategy is to use Federated Learning, a machine learning technique for privacy-preserving distributed training. In Federated Learning, a subset of users will be selected for training model using data at local systems, the server will securely aggregate the computing result from local models to generate a global model, finally that model will give recommendations to users. In this paper, we present a novel algorithm to train Collaborative Filtering recommender system specialized for the ranking task in Federated Learning setting, where the goal is to protect user interaction information (i.e., implicit feedback). Specifically, with the help of the algorithm, the recommender system will be trained by Neural Collaborative Filtering, one of the state-of-the-art matrix factorization methods and Bayesian Personalized Ranking, the most common pairwise approach. In contrast to existing approaches which protect user privacy by requiring users to download/upload the information associated with all interactions that they can possibly interact with in order to perform training, the algorithm can protect user privacy at low communication cost, where users only need to obtain/transfer the information related to a small number of interactions per training iteration. Above all, through extensive experiments, the algorithm has demonstrated to utilize user data more efficient than the most recent research called FedeRank, while ensuring that user privacy is still preserved.

The volume of SMS messages sent on a daily basis globally has continued to grow significantly over the past years. Hence, mobile phones are becoming increasingly vulnerable to SMS spam messages, thereby exposing users to the risk of fraud and theft of personal data. Filtering of messages to detect and eliminate SMS spam is now a critical functionality for which different types of machine learning approaches are still being explored. In this paper, we propose a system for detecting SMS spam using a semi-supervised novelty detection approach based on one class SVM classifier. The system is built as an anomaly detector that learns only from normal SMS messages thus enabling detection models to be implemented in the absence of labelled SMS spam training examples. We evaluated our proposed system using a benchmark dataset consisting of 747 SMS spam and 4827 non-spam messages. The results show that our proposed method out-performed the traditional supervised machine learning approaches based on binary, frequency or TF-IDF bag-of-words. The overall accuracy was 98% with 100% SMS spam detection rate and only around 3% false positive rate.

Recently, hardware Trojan has become a serious security concern in the integrated circuit (IC) industry. Due to the globalization of semiconductor design and fabrication processes, ICs are highly vulnerable to hardware Trojan insertion by malicious third-party vendors. Therefore, the development of effective hardware Trojan detection techniques is necessary. Testability measures have been proven to be efficient features for Trojan nets classification. However, most of the existing machine-learning-based techniques use supervised learning methods, which involve time-consuming training processes, need to deal with the class imbalance problem, and are not pragmatic in real-world situations. Furthermore, no works have explored the use of anomaly detection for hardware Trojan detection tasks. This paper proposes a semi-supervised hardware Trojan detection method at the gate level using anomaly detection. We ameliorate the existing computation of the Sandia Controllability/Observability Analysis Program (SCOAP) values by considering all types of D flip-flops and adopt semi-supervised anomaly detection techniques to detect Trojan nets. Finally, a novel topology-based location analysis is utilized to improve the detection performance. Testing on 17 Trust-Hub Trojan benchmarks, the proposed method achieves an overall 99.47% true positive rate (TPR), 99.99% true negative rate (TNR), and 99.99% accuracy.

Cyber-Physical Systems (CPS) have a physical part that can interact with sensors and actuators. The data that is read from sensors and the one generated to drive actuators is crucial for the correct operation of this class of devices. Most implementations trust the data being read from sensors and the outputted data to actuators. Real-time validation of the input and output of data for any system is crucial for the safety of its operation. This paper proposes an architecture for handling this issue through smart data guards detached from sensors and controllers and acting solely on the data. This mitigates potential issues of malfunctioning sensors and intentional sensor and controller attacks. The data guards understand the expected data, can detect anomalies and can correct them in real-time. This approach adds more guarantees for fault-tolerant behavior in the presence of attacks and sensor failures.

The number of publications related to Explainable Artificial Intelligence (XAI) has increased rapidly this last decade. However, the subjective nature of explainability has led to a lack of consensus regarding commonly used definitions for explainability and with differing problem statements falling under the XAI label resulting in a lack of comparisons. This paper proposes in broad terms a simple comparison framework for XAI methods based on the output and what we call the practical attributes. The aim of the framework is to ensure that everything that can be held constant for the purpose of comparison, is held constant and to ignore many of the subjective elements present in the area of XAI. An example utilizing such a comparison along the lines of the proposed framework is performed on local, post-hoc, model-agnostic XAI algorithms which are designed to measure the feature importance/contribution for a queried instance. These algorithms are assessed on two criteria using synthetic datasets across a range of classifiers. The first is based on selecting features which contribute to the underlying data structure and the second is how accurately the algorithms select the features used in a decision tree path. The results from the first comparison showed that when the classifier was able to pick up the underlying pattern in the model, the LIME algorithm was the most accurate at selecting the underlying ground truth features. The second test returned mixed results with some instances in which the XAI algorithms were able to accurately return the features used to produce predictions, however this result was not consistent.

Vulnerability discovery is an important field of computer security research and development today. Because most of the current vulnerability discovery methods require large-scale manual auditing, and the code parsing process is cumbersome and time-consuming, the vulnerability discovery effect is reduced. Therefore, for the uncertainty of vulnerability discovery itself, it is the most basic tool design principle that auxiliary security analysts cannot completely replace them. The purpose of this paper is to study the source code vulnerability discovery method based on graph neural network. This paper analyzes the three processes of data preparation, source code vulnerability mining and security assurance of the source code vulnerability mining method, and also analyzes the suspiciousness and particularity of the experimental results. The empirical analysis results show that the types of traditional source code vulnerability mining methods become more concise and convenient after using graph neural network technology, and we conducted a survey and found that more than 82% of people felt that the design source code vulnerability mining method used When it comes to graph neural networks, it is found that the design efficiency has become higher.

Aim: To bring off the spam detection in social media using Support Vector Machine (SVM) algorithm and compare accuracy with Artificial Neural Network (ANN) algorithm sample size of dataset is 5489, Initially the dataset contains several messages which includes spam and ham messages 80% messages are taken as training and 20% of messages are taken as testing. Materials and Methods: Classification was performed by KNN algorithm (N=10) for spam detection in social media and the accuracy was compared with SVM algorithm (N=10) with G power 80% and alpha value 0.05. Results: The value obtained in terms of accuracy was identified by ANN algorithm (98.2%) and for SVM algorithm (96.2%) with significant value 0.749. Conclusion: The accuracy of detecting spam using the ANN algorithm appears to be slightly better than the SVM algorithm.

Security is undoubtedly the most serious problem for Web applications, and SQL injection (SQLi) attacks are one of the most damaging. The detection of SQL blind injection vulnerability is very important, but unfortunately, it is not fast enough. This is because time-based SQL blind injection lacks web page feedback, so the delay function can only be set artificially to judge whether the injection is successful by observing the response time of the page. However, brute force cracking and binary search methods used in injection require more web requests, resulting in a long time to obtain database information in SQL blind injection. In this paper, a gated recurrent neural network-based SQL blind injection technology is proposed to generate the predictive characters in SQL blind injection. By using the neural language model based on deep learning and character sequence prediction, the method proposed in this paper can learn the regularity of common database information, so that it can predict the next possible character according to the currently obtained database information, and sort it according to probability. In this paper, the training model is evaluated, and experiments are carried out on the shooting range to compare the method used in this paper with sqlmap (the most advanced sqli test automation tool at present). The experimental results show that the method used in this paper is more effective and significant than sqlmap in time-based SQL blind injection. It can obtain the database information of the target site through fewer requests, and run faster.

This paper belongs to a sequence of manuscripts that discuss generic and easy-to-apply security metrics for Strong PUFs. These metrics cannot and shall not fully replace in-depth machine learning (ML) studies in the security assessment of Strong PUF candidates. But they can complement the latter, serve in initial PUF complexity analyses, and are much easier and more efficient to apply: They do not require detailed knowledge of various ML methods, substantial computation times, or the availability of an internal parametric model of the studied PUF. Our metrics also can be standardized particularly easily. This avoids the sometimes inconclusive or contradictory findings of existing ML-based security test, which may result from the usage of different or non-optimized ML algorithms and hyperparameters, differing hardware resources, or varying numbers of challenge-response pairs in the training phase.This first manuscript within the abovementioned sequence treats one of the conceptually most straightforward security metrics on that path: It investigates the effects that small perturbations in the PUF-challenges have on the resulting PUF-responses. We first develop and implement several sub-metrics that realize this approach in practice. We then empirically show that these metrics have surprising predictive power, and compare our obtained test scores with the known real-world security of several popular Strong PUF designs. The latter include (XOR) Arbiter PUFs, Feed-Forward Arbiter PUFs, and (XOR) Bistable Ring PUFs. Along the way, our manuscript also suggests techniques for representing the results of our metrics graphically, and for interpreting them in a meaningful manner.

With the widespread deployment of data-driven services, the demand for data volumes continues to grow. At present, many applications lack reliable human supervision in the process of data collection, which makes the collected data contain low-quality data or even malicious data. This low-quality or malicious data make AI systems potentially face much security challenges. One of the main security threats in the training phase of machine learning is data poisoning attacks, which compromise model integrity by contaminating training data to make the resulting model skewed or unusable. This paper reviews the relevant researches on data poisoning attacks in various task environments: first, the classification of attacks is summarized, then the defense methods of data poisoning attacks are sorted out, and finally, the possible research directions in the prospect.

To train new staff to be efficient and ready for the tasks assigned is vital. They must be equipped with knowledge and skills so that they can carry out their responsibility to ensure smooth daily working activities. As transitioning to IPv6 has taken place for more than a decade, it is understood that having a dual-stack network is common in any organization or enterprise. However, many Internet users may not realize the importance of IPv6 security due to a lack of awareness and knowledge of cyber and computer security. Therefore, this paper presents an approach to educating people by introducing a security mechanisms model that can be applied in handling security challenges via network sandboxing by setting up an isolated dual stack network testbed using GNS3 to perform network security analysis. The finding shows that applying security mechanisms such as access control lists (ACLs) and host-based firewalls can help counter the attacks. This proves that knowledge and skills to handle dual-stack security are crucial. In future, more kinds of attacks should be tested and also more types of security mechanisms can be applied on a dual-stack network to provide more information and to provide network engineers insights on how they can benefit from network sandboxing to sharpen their knowledge and skills.

Trip planning, which targets at planning a trip consisting of several ordered Points of Interest (POIs) under user-provided constraints, has long been treated as an important application for location-based services. The goal of trip planning is to maximize the chance that the users will follow the planned trip while it is difficult to directly quantify and optimize the chance. Conventional methods either leverage statistical analysis to rank POIs to form a trip or generate trips following pre-defined objectives based on constraint programming to bypass such a problem. However, these methods may fail to reflect the complex latent patterns hidden in the human mobility data. On the other hand, though there are a few deep learning-based trip recommendation methods, these methods still cannot handle the time budget constraint so far. To this end, we propose a TIme-aware Neural Trip Planning (TINT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate trips under given constraints. Then, we propose a specially-designed reinforcement learning (RL) paradigm to directly optimize the objective to obtain an optimal trip generator. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Subsequently, to ensure the feedback from the discriminator is always instructive, we integrate an adversarial learning strategy into the RL paradigm to update the trip generator and the discriminator alternately. Moreover, we devise a novel pre-training schema to speed up the convergence for an efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our framework, which shows that TINT could remarkably outperform the state-of-the-art baselines within short response time.

Axie infinity is a complicated card game with a huge-scale action space. This makes it difficult to solve this challenge using generic Reinforcement Learning (RL) algorithms. We propose a hybrid RL framework to learn action representations and game strategies. To avoid evaluating every action in the large feasible action set, our method evaluates actions in a fixed-size set which is determined using action representations. We compare the performance of our method with two baseline methods in terms of their sample efficiency and the winning rates of the trained models. We empirically show that our method achieves an overall best winning rate and the best sample efficiency among the three methods.

This paper proposes a new two-stage encryption method to increase the cryptographic strength of the AES algorithm, which is based on stochastic error of a neural network. The composite encryption key in AES neural network cryptosystem are the weight matrices of synaptic connections between neurons and the metadata about the architecture of the neural network. The stochastic nature of the prediction error of the neural network provides an ever-changing pair key-ciphertext. Different topologies of the neural networks and the use of various activation functions increase the number of variations of the AES neural network decryption algorithm. The ciphertext is created by the forward propagation process. The encryption result is reversed back to plaintext by the reverse neural network functional operator.

In recent years, technological advancements in the AI and VR fields have increasingly often been paired with considerations on ethics and safety aimed at mitigating unintentional design failures. However, cybersecurity-oriented AI and VR safety research has emphasized the need to additionally appraise instantiations of intentional malice exhibited by unethical actors at pre- and post-deployment stages. On top of that, in view of ongoing malicious deepfake developments that can represent a threat to the epistemic security of a society, security-aware AI and VR design strategies require an epistemically-sensitive stance. In this vein, this paper provides a theoretical basis for two novel AIVR safety research directions: 1) VR as immersive testbed for a VR-deepfake-aided epistemic security training and 2) AI as catalyst within a deepfake-aided so-called cyborgnetic creativity augmentation facilitating an epistemically-sensitive threat modelling. For illustration, we focus our use case on deepfake text – an underestimated deepfake modality. In the main, the two proposed transdisciplinary lines of research exemplify how AIVR safety to defend against unethical actors could naturally converge toward AIVR ethics whilst counteracting epistemic security threats.

False news has become widespread in the last decade in political, economic, and social dimensions. This has been aided by the deep entrenchment of social media networking in these dimensions. Facebook and Twitter have been known to influence the behavior of people significantly. People rely on news/information posted on their favorite social media sites to make purchase decisions. Also, news posted on mainstream and social media platforms has a significant impact on a particular country’s economic stability and social tranquility. Therefore, there is a need to develop a deceptive system that evaluates the news to avoid the repercussions resulting from the rapid dispersion of fake news on social media platforms and other online platforms. To achieve this, the proposed system uses the preprocessing stage results to assign specific vectors to words. Each vector assigned to a word represents an intrinsic characteristic of the word. The resulting word vectors are then applied to RNN models before proceeding to the LSTM model. The output of the LSTM is used to determine whether the news article/piece is fake or otherwise.

The value and size of information exchanged through dark-web pages are remarkable. Recently Many researches showed values and interests in using machine-learning methods to extract security-related useful knowledge from those dark-web pages. In this scope, our goals in this research focus on evaluating best prediction models while analyzing traffic level data coming from the dark web. Results and analysis showed that feature selection played an important role when trying to identify the best models. Sometimes the right combination of features would increase the model’s accuracy. For some feature set and classifier combinations, the Src Port and Dst Port both proved to be important features. When available, they were always selected over most other features. When absent, it resulted in many other features being selected to compensate for the information they provided. The Protocol feature was never selected as a feature, regardless of whether Src Port and Dst Port were available.

This paper deals with the problem of image forgery detection because of the problems it causes. Where The Fake im-ages can lead to social problems, for example, misleading the public opinion on political or religious personages, de-faming celebrities and people, and Presenting them in a law court as evidence, may Doing mislead the court. This work proposes a deep learning approach based on Deep CNN (Convolutional Neural Network) Architecture, to detect fake images. The network is based on a modified structure of Xception net, CNN based on depthwise separable convolution layers. After extracting the feature maps, pooling layers are used with dense connection with Xception output, to in-crease feature maps. Inspired by the idea of a densenet network. On the other hand, the work uses the YCbCr color system for images, which gave better Accuracy of %99.93, more than RGB, HSV, and Lab or other color systems.

The rise of social media has brought the rise of fake news and this fake news comes with negative consequences. With fake news being such a huge issue, efforts should be made to identify any forms of fake news however it is not so simple. Manually identifying fake news can be extremely subjective as determining the accuracy of the information in a story is complex and difficult to perform, even for experts. On the other hand, an automated solution would require a good understanding of NLP which is also complex and may have difficulties producing an accurate output. Therefore, the main problem focused on this project is the viability of developing a system that can effectively and accurately detect and identify fake news. Finding a solution would be a significant benefit to the media industry, particularly the social media industry as this is where a large proportion of fake news is published and spread. In order to find a solution to this problem, this project proposed the development of a fake news identification system using deep learning and natural language processing. The system was developed using a Word2vec model combined with a Long Short-Term Memory model in order to showcase the compatibility of the two models in a whole system. This system was trained and tested using two different dataset collections that each consisted of one real news dataset and one fake news dataset. Furthermore, three independent variables were chosen which were the number of training cycles, data diversity and vector size to analyze the relationship between these variables and the accuracy levels of the system. It was found that these three variables did have a significant effect on the accuracy of the system. From this, the system was then trained and tested with the optimal variables and was able to achieve the minimum expected accuracy level of 90%. The achieving of this accuracy levels confirms the compatibility of the LSTM and Word2vec model and their capability to be synergized into a single system that is able to identify fake news with a high level of accuracy.