Pusat IPv6 Termaju Negara - Tesis

Browse

Recent Submissions

Now showing 1 - 5 of 45
  • Thumbnail Image
    Publication
    Secured Communication Mechanism For Message Authentication And Data Confidentiality In Secs/Gem Protocol
    (2024-03)
    Jaisan S. M., Ashish
    This study proposes SECS/GEM-AE, a mechanism for securing SECS/GEM data messages using AES-GCM encryption and evaluates its performance against the standard SECS/GEM protocol and SECS/GEMsec, a security mechanism proposed to authenticate SECS/GEM messages.
  • Thumbnail Image
    Publication
    Passive Rule-Based Approach To Detect Sinkhole Attack In 6lowpan Rpl Based Internet Of Things Networks
    (2024-02)
    Subh, Al Sarawi Shadi Mustafa
    The aim of this thesis is to propose a Passive Rule-Based Approach named PRBA to detect sinkhole attacks in 6LoWPAN RPL-based IoT Networks, which consists of four stages to achieve four research objectives, which are: (1) Data collection and preprocessing stage that fulfills the objective to transform the collected power consumption values and the captured ICMPv6 network traffic into a meaningful format; (2) Feature Selection stage that fulfills the objective to decrease the size of the features by selecting the most significant features that contribute to detecting sinkhole attacks; (3) Behavioral Indicators stage that fulfills the objective to identify abnormal behavior of sinkhole attacks using the features of the ICMPv6 and power consumption from the previous stage; and (4) Sinkhole Attack Detection stage that fulfills the objective to decide whether there is a sinkhole attack in two steps.
  • Thumbnail Image
    Publication
    Approach For Optimizing Course Recommendation Based On Integrating Modified Felder-Silverman Learning Style Model With Meta-Heuristics Algorithm
    (2023-12)
    Ashraf, Erum
    E-learning's popularity surges due to technology, flooding Massive Open Online Course (MOOC) platforms with courses, causing information overload. Recommender systems filter courses but struggle with learning styles due to lack of standardized datasets and measurement approaches, hindering data collection in resource-constrained educational institutions. This research streamlines course selection by matching it with learners' styles. It involves identifying potential courses learning style, validated through genetic and surrogate meta-heuristics optimization algorithms, and employing Felder-Silverman model for learning style identification. The proposed scheme supported the personalized course recommendations to students suitable with student learning style.
  • Thumbnail Image
    Publication
    Enhanced Steganography Framework Based On Lossless Compression And Histogram
    (2024-07)
    Mohammad Kasasbeh, Dima Suliman
    Steganography is an effective cybersecurity technique that facilitates covert communication by hiding information's existence within a spoof image. The trade-off between embedding capacity, imperceptibility, and reversibility has presented a new challenge in steganography. Balancing these factors is crucial and essential for the development of effective steganography. This thesis proposes an enhanced steganography framework to increase embedding capacity, maintain imperceptibility, and achieve reversibility. Three models were proposed: compression, embedding map generation, and reversible steganography. The compression model was modified to include a hybrid lossless text compression algorithm to reduce redundant secret information and boost embedding capacity. The Embedding Map Generation Model proposed two techniques to determine the best RGB channels and generate the embedding location map before the embedding process. In the reversible steganography model, a 3D embedding process is proposed. It hides compressed bitstreams in the 2D-PEH with a lower local complexity value. Additionally, it hides decompression keys along with other extraction parameters using the generated embedding location map.
  • Thumbnail Image
    Publication
    Visual Semantic Context-aware Attention-based Dialog Model
    (2024-09)
    Eugene, Tan Boon Hong
    Visual dialogue dataset, i.e. VisDial v1.0 includes a wide range of Microsoft Common Objects in Context (MSCOCO) image contents and collected questions via a crowdsourcing marketplace platform (i.e. Amazon Mechanical Turk). The use of existing question history and images no longer contributes to a better understanding of the image context as they do not cover the entire image semantic context. This research proposes the DsDial dataset, which is a context-aware visual dialogue that groups all relevant dialogue histories extracted based on their respective MSCOCO image categories. This research also exploits the overlapping visual context between images via adaptive relevant dialogue history selection during new dataset generation based on the groups of all relevant dialogue histories. It is half of 2.6 million question-answer pairs. Meanwhile, this research proposes Diverse History-Dialog (DS-Dialog) to resolve the missing visual semantic information for each image via context-aware visual attention. The context-aware visual attention includes the question-guided and relevant-dialoguehistory- guided visual attention modules to get the relevant visual context when both have achieved great confidence. The qualitative and quantitative experimental results on the VisDial v1.0 and DsDial datasets demonstrate that the proposed DS-Dialog not only outperforms the existing methods, but also achieves a competitive results by contributing to a better visual semantic extraction. DsDial dataset has proven its significance on LF model as compared to VisDal v1.0. Overall quantitative results show that DS-Dialog with DsDial dataset has achieved the best test scores for recall@1, recall@5, recall@10, mean rank, MRR, and NDCG respectively.