Anomalous query access detection in RBAC-administered databases with random forest and PCA

Ronao, Charissa Ann; Cho, Sung-Bae

doi:10.1016/j.ins.2016.06.038

Cited by 44 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In late advancements, Ranao et. al [18] introduced a Query Access location approach utilizing Random Forest and PCA to lessen information dimensionality and create just important and unrelated information. As the dimensionality is decreased, both, the framework execution and True Positive rate increments…”

Section: Related Workmentioning

confidence: 99%

Database Intrusion Detection using Role and User Level Sequential Pattern Mining and Fuzzy Clustering

Singh¹,

Singhal²,

Kumar³

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

Majority of the present-day organizations store and use data on large scale for their functioning. Often this data is private and essential, and unauthorized access to the data can have serious financial and legal repercussions. While it is easier to capture malicious activities perpetrated by an external agent, it is relatively harder to detect transactions committed by company employee with some malicious intent. This is due to the awareness of the employee about the company database structure along with their authorized access privileges. We propose a novel intrusion detection system called user and role-level cluster-based intrusion detection system (URCIDS). We analyze the user behavior at role and user level, to check if the transaction under consideration is in accordance to the regular behavior of the user. We flag transactions that violate the general access pattern followed by the user. A detailed experimental analysis shows that we are able to gain a higher accuracy than most of the state-of-the-art methodologies proposed in this field of study.

show abstract

Section: Related Workmentioning

confidence: 99%

Database Intrusion Detection using Role and User Level Sequential Pattern Mining and Fuzzy Clustering

Singh¹,

Singhal²,

Kumar³

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

show abstract

“…Genetic algorithm (GA) belongs to a large class of evolutionary algorithms, which is a metaheuristic algorithm inspired by the process of natural selection. Compared with commonly used methods like principal component analysis (PCA) that uses an orthogonal transformation to produce uncorrelated and relevant features [ 32 ], and singular value decomposition (SVD) that factorizes a single matrix into three matrices, GA has an automatic learning process aimed at achieving good feature group selection. It is commonly used to generate high-quality solutions to optimization and search problems by relying on bio-inspired operators, such as mutation, crossover, and selection [ 33 ].…”

Section: Feature Extractionmentioning

confidence: 99%

Feature-Level Fusion of Surface Electromyography for Activity Monitoring

Tang

Luo

2018

Sensors

View full text Add to dashboard Cite

Surface electromyography (sEMG) signals are commonly used in activity monitoring and rehabilitation applications as they reflect effectively the motor intentions of users. However, real-time sEMG signals are non-stationary and vary to a large extent within the time frame of signals. Although previous studies have focused on the issues, their results have not been satisfactory. Therefore, we present a new method of conducting feature-level fusion to obtain a new feature space for sEMG signals. Eight activities of daily life (ADLs), including falls, were performed to obtain raw data from EMG signals from the lower limb. A feature set combining the time domain, time–frequency domain, and entropy domain was applied to the raw data to establish an initial feature space. A new projection method, the weighting genetic algorithm for GCCA (WGA-GCCA), was introduced to obtain the final feature space. Different tests were carried out to evaluate the performance of the new feature space. The new feature space created with the WGA-GCCA effectively reduced the dimensions and selected the best feature vectors dynamically while improving monotonicity. The Davies–Bouldin index (DBI) based on fuzzy c-means algorithms of the space obtained the lowest value compared with several fusion methods. It also achieved the highest accuracy when applied to support vector machine classifier.

show abstract

“…Usually data blocks accessed by the user are not uniformly distributed over the set of data blocks outsourced at the server. The Zipf distribution is often used to model a non-uniform access to a database [42][43][44][45]. The Zipf distribution is also known as the 80:20 or 90:10 law.…”

Section: Path Oram Enhancementmentioning

confidence: 99%

“…The parameter α (α > 0) plays a major role in the Zipf distribution as it determines the shape of the cumulative probability function and regulates the deterioration in requests frequencies [42,[45][46][47][48]. This parameter α can have different values for different applications.…”

Section: Path Oram Enhancementmentioning

confidence: 99%

Locality Aware Path ORAM: Implementation, Experimentation and Analytical Modeling

Al-Saleh

Belghith

2018

Computers

View full text Add to dashboard Cite

In this paper, we propose an advanced implementation of Path ORAM to hide the access pattern to outsourced data into the cloud. This implementation takes advantage of eventual data locality and popularity by introducing a small amount of extra storage at the client side. Two replacement strategies are used to manage this extra storage (cache): the Least Recently Used (LRU) and the Least Frequently Used (LFU). Using the same test bed, conducted experiments clearly show the superiority of the advanced implementation compared to the traditional Path ORAM implementation, even for a small cache size and reduced data locality. We then present a mathematical model that provides closed form solutions when data requests follow a Zipf distribution with non-null parameter. This model is showed to have a small and acceptable relative error and is then well validated by the conducted experimental results.

show abstract

Anomalous query access detection in RBAC-administered databases with random forest and PCA

Cited by 44 publications

References 24 publications

Database Intrusion Detection using Role and User Level Sequential Pattern Mining and Fuzzy Clustering

Database Intrusion Detection using Role and User Level Sequential Pattern Mining and Fuzzy Clustering

Feature-Level Fusion of Surface Electromyography for Activity Monitoring

Locality Aware Path ORAM: Implementation, Experimentation and Analytical Modeling

Contact Info

Product

Resources

About