Man-In-Middle Attack/for a Free Scale Topology

Umamaheshwari, S.; Swaminathan, Jaichander

doi:10.1109/iccci.2018.8441202

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a) If the cloud platform provider is untrusted, it can manipulate the training dataset and baseline neural networks or ML algorithms. b) Even if the cloud platform provider is trusted, a man-in-middle [18] attack can be performed by another client to steal the IP, i.e., the trained network or even to manipulate the IP or affect the training process. 2) IP Providers: The other actor in the manufacturing cycle is the IP provider which can also be untrusted because it can poison the training datasets and can also manipulate baseline ML models/architectures or other hyper-parameters, which are not accessible to 3P cloud providers.…”

Section: ) 3 Rd Party (3p) Cloud Platformsmentioning

confidence: 99%

“…a) If the cloud platform provider is untrusted, it can manipulate the training dataset and baseline neural networks or ML algorithms. b) Even if the cloud platform provider is trusted, a man-in-middle [18] attack can be performed by another client to steal the IP, i.e., the trained network or even to manipulate the IP or affect the training process. Thus, based on the trustworthiness of all actors involved in the design/manufacturing cycle, there can be 15 possible threat models for ML-based systems.…”

Section: A Threat Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Security for Machine Learning-Based Systems: Attacks and Challenges During Training and Inference

Khalid

Hanif

Rehman

et al. 2018

2018 International Conference on Frontiers of Information Technology (FIT)

View full text Add to dashboard Cite

The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although MLbased solutions address the efficient computing requirements of big data, they introduce (new) security vulnerabilities into the systems, which cannot be addressed by traditional monitoringbased security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB), respectively. Moreover, based on the security analysis of ML-training, we also propose an attack that has a very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats.

show abstract

Section: ) 3 Rd Party (3p) Cloud Platformsmentioning

confidence: 99%

“…a) If the cloud platform provider is untrusted, it can manipulate the training dataset and baseline neural networks or ML algorithms. b) Even if the cloud platform provider is trusted, a man-in-middle [18] attack can be performed by another client to steal the IP, i.e., the trained network or even to manipulate the IP or affect the training process. Thus, based on the trustworthiness of all actors involved in the design/manufacturing cycle, there can be 15 possible threat models for ML-based systems.…”

Section: A Threat Modelsmentioning

confidence: 99%

Security for Machine Learning-Based Systems: Attacks and Challenges During Training and Inference

Khalid

Hanif

Rehman

et al. 2018

2018 International Conference on Frontiers of Information Technology (FIT)

View full text Add to dashboard Cite

show abstract

“…The small-world feature refers to the short characteristic path length as well as the high clustering coefficient in the network. It is noteworthy that the complex artificial neural networks such as associative memory systems [18] using the small-world phenomenon, and the scalefree property [19,20] have better efficiency in time and memory capacity than the randomly connected networks with similar connections. Also, the chaotic time series prediction problem by the small-world trait and the scale-free property can be solved more efficiently [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Design of a reservoir for cloud-enabled echo state network with high clustering coefficient

Akrami

Rostami

Khosravi

2020

J Wireless Com Network

View full text Add to dashboard Cite

Reservoir computing (RC) is considered as a suitable alternative for descending gradient methods in recursive neural networks (RNNs) training. The echo state network (ESN) is a platform for RC and nonlinear system simulation in the cloud environment with many external users. In the past researches, the highest eigenvalue of reservoir connection weight (spectral radius) was used to predict reservoir dynamics. Some researchers have illustrated; the characteristics of scale-free and small-world can improve the approximation capability in echo state networks; however, recent studies have shown importance of the infrastructures such as clusters and the stability criteria of these reservoirs as altered. In this research, we suggest a high clustered ESN called HCESN that its internal neurons are interconnected in form of clusters. Each of the clusters contains one backbone and a number of local nodes. We implemented a classical clustering algorithm, called K-means, and three optimization algorithms including genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO) to improve the clustering efficiency of the new reservoir and compared them with each other. For investigating the spectral radius and predictive power of the resulting reservoirs, we also applied them to the laser time series and the Mackey-Glass dynamical system. It is demonstrated that new clustered reservoirs have some specifications of biologic neural systems and complex networks like average short path length, high clustering coefficient, and power-law distribution. The empirical results illustrated that the ESN based on PSO could strikingly enhance echo state property (ESP) and obtains less chaotic time series prediction error compared with other works and the original version of ESN. Therefore, it can approximate nonlinear dynamical systems and predict the chaotic time series.

show abstract