Demystify the Gravity Well in the Optimization Landscape (Student Abstract)

Dou, Jason; Bao, Runxue; Song, Siyu; Yang, Shuran; Zhang, Yanfu; Liang, Paul Pu; Mao, Haiyi Harry

doi:10.1609/aaai.v37i13.26961

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most existing chaotic systems are traditional chaotic systems that encounter issues such as a small key space and a lack of capability to resist brute force attacks, statistical attacks, and differential attacks. Particularly in light of the developing deep learning landscape [11][12][13], the capacity to analyze complex issues has grown. Therefore, the pursuit of more secure and efficient encryption schemes is an appealing research direction [14].…”

Section: Introductionmentioning

confidence: 99%

A Novel Eighth-Order Hyperchaotic System and Its Application in Image Encryption

Qiu,

Zhang,

Yue

et al. 2023

Mathematics

View full text Add to dashboard Cite

With the advancement in information and communication technologies (ICTs), the widespread dissemination and sharing of digital images has raised concerns regarding privacy and security. Traditional methods of encrypting images often suffer from limitations such as a small key space and vulnerability to brute-force attacks. To address these issues, this paper proposes a novel eighth-order hyperchaotic system. This hyperchaotic system exhibits various dynamic behaviors, including hyperchaos, sub-hyperchaos, and chaos. The encryption scheme based on this system offers a key space larger than 22338. Through a comprehensive analysis involving histogram analysis, key space analysis, correlation analysis, entropy analysis, key sensitivity analysis, differential attack analysis, and cropping attack analysis, it is demonstrated that the proposed system is capable of resisting statistical attacks, brute force attacks, differential attacks, and cropping attacks, thereby providing excellent security performance.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Eighth-Order Hyperchaotic System and Its Application in Image Encryption

Qiu,

Zhang,

Yue

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

A novel image encryption scheme based on ccnn

Zhang,

Sun,

Geng

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

With the advancement of computational capacity, the key space will become one of the crucial factors influencing the security of digital cryptographic systems. Despite chaotic-based digital cryptographic systems possessing large key spaces, the post-Moore's era rapid growth in computational capacity continues to pose challenges to the security of chaotic-based cryptographic systems. To address this issue, a novel image encryption scheme based on non-autonomous chaotic system is presented in this paper. In particular, a brain inspired neuron called continuous-coupled neural network (CCNN) is utilized to design image encryption scheme. To achieve the efficient image encryption scheme, firstly, the CCNN model is simplified to uncoupled-linking neuron model. The dynamic behavior under various driving signals is studied. The analysis showed that uncoupled-linking CCNN neuron exhibit various dynamic behavior under sine waves, triangular waves, sawtooth, superimposed sine waves, etc. Secondly, the decorrelation operation method is utilized to enhance the pseudo-randomness of the sequence. On this basis, thirdly, the image encryption scheme is proposed. It uses bit-level pixel scrambling, row scrambling, column scrambling and diffusion to modify the pixel value and the pixel position of the image. Security analysis shows that the proposed scheme is able to resist differential attack, statistics attack, known-plaintext attack and brute force attack. Moreover, the key space of the proposed scheme can be extended by the combination of drive signals. This unique feature makes the key space of the proposed scheme to be infinite, leading this kind of chaos-based cryptographic system to be a competitive candidate in post-Moore's era.

show abstract

Robust and Accurate Doublet Detection of Single-Cell Sequencing Data via Maximizing Area Under Precision-Recall Curve

Chen,

Wu,

et al. 2023

Preprint

View full text Add to dashboard Cite

Single-cell sequencing has revolutionized our understanding of cellular heterogeneity by offering detailed profiles of individual cells within diverse specimens. However, due to the limitations of sequencing technology, two or more cells may be captured in the same droplet and share the same barcode. These incidents, termed doublets or multiplets, can lead to artifacts in single-cell data analysis. While explicit experimental design can mitigate these issues with the help of auxiliary cell markers, computationally annotating doublets has a broad impact on analyzing the existing public single-cell data and reduces potential experimental costs. Considering that doublets form only a minor fraction of the total dataset, we argue that current doublet detection methods, primarily focused on optimizing classification accuracy, might be inefficient in performing well on the inherently imbalanced data in the area under the precision-recall curve (AUPRC) metric. To address this, we introduce RADO (Robust and Accurate DOublet detection) - an algorithm designed to annotate doublets by maximizing the AUPRC, effectively tackling the imbalance challenge. Benchmarked on 18 public datasets, RADO outperforms other methods in terms of doublet score and achieves similar performance to the current best methods in doublet calling. Furthermore, beyond its application in single-cell RNA-seq data, we demonstrate RADO’s adaptability to single-cell assays for transposase-accessible chromatin sequencing (scATAC-seq) data, where it outperforms other scATAC-seq doublet detection methods. RADO’s open-source implementation is available at:https://github.com/poseidonchan/RADO.

show abstract

Demystify the Gravity Well in the Optimization Landscape (Student Abstract)

Cited by 4 publications

References 6 publications

A Novel Eighth-Order Hyperchaotic System and Its Application in Image Encryption

A Novel Eighth-Order Hyperchaotic System and Its Application in Image Encryption

A novel image encryption scheme based on ccnn

Robust and Accurate Doublet Detection of Single-Cell Sequencing Data via Maximizing Area Under Precision-Recall Curve

Contact Info

Product

Resources

About