Data complexity-based batch sanitization method against poison in distributed learning

The security of Federated Learning(FL)/Distributed Machine Learning(DML)is gravely threatened by data poisoning attacks,which destroy the usability of the model by contaminating training samples,so such attacks are called causative availability indiscriminate attacks.Facing the problem that existing data sanitization methods are hard to apply to real-time applications due to their tedious process and heavy computations,we propose a new supervised batch detection method for poison,which can fleetly sanitize the training dataset before the local model training.We design a training dataset generation method that helps to enhance accuracy and uses data complexity features to train a detection model,which will be used in an efficient batch hierarchical detection process.Our model stockpiles knowledge about poison,which can be expanded by retraining to adapt to new attacks.Being neither attack-specific nor scenario-specific,our method is applicable to FL/DML or other online or offline scenarios.

Securing Consumer Internet of Things for Botnet Attacks: Deep Learning Approach

DDoS attacks in the Internet of Things(IoT)technology have increased significantly due to its spread adoption in different industrial domains.The purpose of the current research is to propose a novel technique for detecting botnet attacks in user-oriented IoT environments.Conspicuously,an attack identification technique inspired by Recurrent Neural networks and Bidirectional Long Short Term Memory(BLRNN)is presented using a unique Deep Learning(DL)technique.For text identification and translation of attack data segments into tokenized form,word embedding is employed.The performance analysis of the presented technique is performed in comparison to the state-of-the-art DL techniques.Specifically,Accuracy(98.4%),Specificity(98.7%),Sensitivity(99.0%),F-measure(99.0%)and Data loss(92.36%)of the presented BLRNN detection model are determined for identifying 4 attacks over Botnet(Mirai).The results show that,although adding cost to each epoch and increasing computation delay,the bidirectional strategy is more superior technique model over different data instances.

A Cyber Kill Chain Approach for Detecting Advanced Persistent Threats

The number of cybersecurity incidents is on the rise despite significant investment in security measures.The existing conventional security approaches have demonstrated limited success against some of the more complex cyber-attacks.This is primarily due to the sophistication of the attacks and the availability of powerful tools.Interconnected devices such as the Internet of Things(IoT)are also increasing attack exposures due to the increase in vulnerabilities.Over the last few years,we have seen a trend moving towards embracing edge technologies to harness the power of IoT devices and 5G networks.Edge technology brings processing power closer to the network and brings many advantages,including reduced latency,while it can also introduce vulnerabilities that could be exploited.Smart cities are also dependent on technologies where everything is interconnected.This interconnectivity makes them highly vulnerable to cyber-attacks,especially by the Advanced Persistent Threat(APT),as these vulnerabilities are amplified by the need to integrate new technologies with legacy systems.Cybercriminals behind APT attacks have recently been targeting the IoT ecosystems,prevalent in many of these cities.In this paper,we used a publicly available dataset on Advanced Persistent Threats(APT)and developed a data-driven approach for detecting APT stages using the Cyber Kill Chain.APTs are highly sophisticated and targeted forms of attacks that can evade intrusion detection systems,resulting in one of the greatest current challenges facing security professionals.In this experiment,we used multiple machine learning classifiers,such as Naïve Bayes,Bayes Net,KNN,Random Forest and Support Vector Machine(SVM).We used Weka performance metrics to show the numeric results.The best performance result of 91.1%was obtained with the Naïve Bayes classifier.We hope our proposed solution will help security professionals to deal with APTs in a timely and effective manner.

Droid Detector:Android Malware Characterization and Detection Using Deep Learning

Smartphones and mobile tablets are rapidly becoming indispensable in daily life. Android has been the most popular mobile operating system since 2012. However, owing to the open nature of Android, countless malwares are hidden in a large number of benign apps in Android markets that seriously threaten Android security. Deep learning is a new area of machine learning research that has gained increasing attention in artificial intelligence. In this study, we propose to associate the features from the static analysis with features from dynamic analysis of Android apps and characterize malware using deep learning techniques. We implement an online deep-learning-based Android malware detection engine（Droid Detector） that can automatically detect whether an app is a malware or not. With thousands of Android apps, we thoroughly test Droid Detector and perform an indepth analysis on the features that deep learning essentially exploits to characterize malware. The results show that deep learning is suitable for characterizing Android malware and especially effective with the availability of more training data. Droid Detector can achieve 96.76% detection accuracy, which outperforms traditional machine learning techniques. An evaluation of ten popular anti-virus softwares demonstrates the urgency of advancing our capabilities in Android malware detection.

A robust adversarial attack against speech recognition with UAP

Speech recognition(SR)systems based on deep neural networks are increasingly widespread in smart devices.However,they are vulnerable to human-imperceptible adversarial attacks,which cause the SR to generate incorrect or targeted adversarial commands.Meanwhile,audio adversarial attacks are particularly susceptible to various factors,e.g.,ambient noise,after applying them to a real-world attack.To circumvent this issue,we develop a universal adversarial perturbation(UAP)generation method to construct robust real-world UAP by integrating ambient noise into the generation process.The proposed UAP can work well in the case of input-agnostic and independent sources.We validate the effectiveness of our method on two different SRs in different real-world scenarios and parameters,the results demonstrate that our method yields state-of-the-art performance,i.e.given any audio waveform,the word error rate can be up to 80%.Extensive experiments investigate the impact of different parameters(e.g,signal-to-noise ratio,distance,and attack angle)on the attack success rate.