Why Globally Re-shuffle? Revisiting Data Shuffling in Large Scale Deep Learning

Nguyen, Truong Thao; Domke, Jens; Drozd, Aleksandr; Vatai, Emil; Liao, Jianwei; Wahib, Mohamed; Gerofi, Balazs

doi:10.1109/ipdps53621.2022.00109

Cited by 15 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many countermeasures, including masking [13][14][15], shuffling [16][17][18], randomized clock [19,20], random delay insertion [21][22][23], constant-weight encoding [24], and code polymorphism [25,26], are used to lessen side-channel assaults. By preventing information from leaking through physically quantifiable channels like time [27,28], power consump-tion [29,30], or electromagnetic radiation [31,32], these countermeasures seek to safeguard cryptographic systems.…”

Section: Of 13mentioning

confidence: 99%

Investigating CRYSTALS-Kyber Vulnerabilities: Attack Analysis and Mitigation

Iavich,

Kuchukhidze

2024

Cryptography

View full text Add to dashboard Cite

Significant advancements have been achieved in the field of quantum computing in recent years. If somebody ever creates a sufficiently strong quantum computer, many of the public-key cryptosystems in use today might be compromised. Kyber is a post-quantum encryption technique that depends on lattice problem hardness, and it was recently standardized. Despite extensive testing by the National Institute of Standards and Technology (NIST), new investigations have demonstrated the effectiveness of CRYSTALS-Kyber attacks and their applicability in non-controlled environments. We investigated CRYSTALS-Kyber’s susceptibility to side-channel attacks. In the reference implementation of Kyber512, additional functions can be compromised by employing the selected ciphertext. The implementation of the selected ciphertext allows the attacks to succeed. Real-time recovery of the entire secret key is possible for all assaults.

show abstract

Section: Of 13mentioning

confidence: 99%

Investigating CRYSTALS-Kyber Vulnerabilities: Attack Analysis and Mitigation

Iavich,

Kuchukhidze

2024

Cryptography

View full text Add to dashboard Cite

show abstract

“…The dataset consists of images displaying various monuments, organized in a directory format where each subdirectory represents a different monument class or category. We utilized TensorFlow's tf.keras.preprocessing.image_dataset_from_directory utility to load the dataset, applying specifications for shuffling [8] , resizing [9], and batching. This process ensures that the dataset is formatted appropriately and ready for subsequent analysis.…”

Section: ) Data Collection and Preparationmentioning

confidence: 99%

Heritage Identification of Monument Using Deep Learning

Labde,

Wakode,

Wakode

et al. 2024

IJRASET

View full text Add to dashboard Cite

There are many beautiful and colorful countries in the world which are famous for their culture and heritage. The historical landmarks of such countries convey a great deal through their magnificent structures and rich heritage. The extensive past and legacy of such nations are apparent in the splendid palaces, fortresses, towers, shrines, and cathedrals that are scattered throughout the entirety of their land. We need to protect cultural monuments and landmarks as they are one of the sources of inspiration for future generations. Traditional methods for monument identification often rely on manual inspection or rudimentary computer vision techniques, which can be time-consuming and error-prone. We can provide the best solutions using modern machine learning and deep learning techniques. In our model, we used an approach based on deep learning for the automated identification of heritage monuments from images. We leveraged the power of convolutional neural networks (CNNs) to extract hierarchical features from monument images and train a classifier to recognize different architectural styles and structures. We evaluated our approach on a dataset comprising diverse monument images collected from public archives and online repositories. We applied various pre-processing techniques such as image resizing, normalization of pixel values, and data augmentation. We analyzed and further improved the model’s performance for heritage identification of monuments.

show abstract

“…This means randomly changing the locations for several samples but keeping the feature values in the same order. Shuffling is essential to eliminate any sort order in the dataset, ensuring the classifier is not overfitting to particular class duo sort order [ 45 ]. Dataset Distribution: This process involves dividing the dataset into training and testing (validation) datasets.…”

Section: Doh Identification Architecturementioning

confidence: 99%

A Lightweight Double-Stage Scheme to Identify Malicious DNS over HTTPS Traffic Using a Hybrid Learning Approach

Al‐Haija

Alohaly

Odeh

2023

Sensors

View full text Add to dashboard Cite

The Domain Name System (DNS) protocol essentially translates domain names to IP addresses, enabling browsers to load and utilize Internet resources. Despite its major role, DNS is vulnerable to various security loopholes that attackers have continually abused. Therefore, delivering secure DNS traffic has become challenging since attackers use advanced and fast malicious information-stealing approaches. To overcome DNS vulnerabilities, the DNS over HTTPS (DoH) protocol was introduced to improve the security of the DNS protocol by encrypting the DNS traffic and communicating it over a covert network channel. This paper proposes a lightweight, double-stage scheme to identify malicious DoH traffic using a hybrid learning approach. The system comprises two layers. At the first layer, the traffic is examined using random fine trees (RF) and identified as DoH traffic or non-DoH traffic. At the second layer, the DoH traffic is further investigated using Adaboost trees (ADT) and identified as benign DoH or malicious DoH. Specifically, the proposed system is lightweight since it works with the least number of features (using only six out of thirty-three features) selected using principal component analysis (PCA) and minimizes the number of samples produced using a random under-sampling (RUS) approach. The experiential evaluation reported a high-performance system with a predictive accuracy of 99.4% and 100% and a predictive overhead of 0.83 µs and 2.27 µs for layer one and layer two, respectively. Hence, the reported results are superior and surpass existing models, given that our proposed model uses only 18% of the feature set and 17% of the sample set, distributed in balanced classes.

show abstract

Why Globally Re-shuffle? Revisiting Data Shuffling in Large Scale Deep Learning

Cited by 15 publications

References 30 publications

Investigating CRYSTALS-Kyber Vulnerabilities: Attack Analysis and Mitigation

Investigating CRYSTALS-Kyber Vulnerabilities: Attack Analysis and Mitigation

Heritage Identification of Monument Using Deep Learning

A Lightweight Double-Stage Scheme to Identify Malicious DNS over HTTPS Traffic Using a Hybrid Learning Approach

Contact Info

Product

Resources

About