Sentiment analysis,a cornerstone of natural language processing,has witnessed remarkable advancements driven by deep learning models which demonstrated impressive accuracy in discerning sentiment from text across vari...Sentiment analysis,a cornerstone of natural language processing,has witnessed remarkable advancements driven by deep learning models which demonstrated impressive accuracy in discerning sentiment from text across various domains.However,the deployment of such models in resource-constrained environments presents a unique set of challenges that require innovative solutions.Resource-constrained environments encompass scenarios where computing resources,memory,and energy availability are restricted.To empower sentiment analysis in resource-constrained environments,we address the crucial need by leveraging lightweight pre-trained models.These models,derived from popular architectures such as DistilBERT,MobileBERT,ALBERT,TinyBERT,ELECTRA,and SqueezeBERT,offer a promising solution to the resource limitations imposed by these environments.By distilling the knowledge from larger models into smaller ones and employing various optimization techniques,these lightweight models aim to strike a balance between performance and resource efficiency.This paper endeavors to explore the performance of multiple lightweight pre-trained models in sentiment analysis tasks specific to such environments and provide insights into their viability for practical deployment.展开更多
Cryptography plays consistently an essential role in securing any sort of communications or data broadcastover the network. Since the security of any designed block cipher algorithm is related to its Substitution box ...Cryptography plays consistently an essential role in securing any sort of communications or data broadcastover the network. Since the security of any designed block cipher algorithm is related to its Substitution box (S-box),several eforts have been made by researchers to design a vigorous S-box that maintains fawlessly the cost, performance, and security trade-of. From the literature, we can fnd a variety of input–output sizes of S-boxes, eachof which has its benefts and drawbacks. Therefore, this work introduces a new S-box pattern generation basedon the chaotic enhanced logistic map where its chaotic behavior ofers good randomness ability, a fact that enhancesits unpredictability. In our realization, the intention was the generation of a 5-bit Sbox due to its suitability and costefectiveness to be integrated into lightweight cryptosystems. Moreover, the S-box security strength is proved by testing it through numerous cryptanalysis measurements. We can mention non-linearity, bijectivity, linearity, diferentialcryptanalysis, boomerang attacks resilience, Avalanche efect, and algebraic attacks resilience. The results showthat our proposition provides good resistance to the aforementioned attacks and even shows superiority over its 5-bitcompetitors in terms of non-linearity, diferential, Boomerang, and algebraic attack resistance.展开更多
文摘Sentiment analysis,a cornerstone of natural language processing,has witnessed remarkable advancements driven by deep learning models which demonstrated impressive accuracy in discerning sentiment from text across various domains.However,the deployment of such models in resource-constrained environments presents a unique set of challenges that require innovative solutions.Resource-constrained environments encompass scenarios where computing resources,memory,and energy availability are restricted.To empower sentiment analysis in resource-constrained environments,we address the crucial need by leveraging lightweight pre-trained models.These models,derived from popular architectures such as DistilBERT,MobileBERT,ALBERT,TinyBERT,ELECTRA,and SqueezeBERT,offer a promising solution to the resource limitations imposed by these environments.By distilling the knowledge from larger models into smaller ones and employing various optimization techniques,these lightweight models aim to strike a balance between performance and resource efficiency.This paper endeavors to explore the performance of multiple lightweight pre-trained models in sentiment analysis tasks specific to such environments and provide insights into their viability for practical deployment.
文摘Cryptography plays consistently an essential role in securing any sort of communications or data broadcastover the network. Since the security of any designed block cipher algorithm is related to its Substitution box (S-box),several eforts have been made by researchers to design a vigorous S-box that maintains fawlessly the cost, performance, and security trade-of. From the literature, we can fnd a variety of input–output sizes of S-boxes, eachof which has its benefts and drawbacks. Therefore, this work introduces a new S-box pattern generation basedon the chaotic enhanced logistic map where its chaotic behavior ofers good randomness ability, a fact that enhancesits unpredictability. In our realization, the intention was the generation of a 5-bit Sbox due to its suitability and costefectiveness to be integrated into lightweight cryptosystems. Moreover, the S-box security strength is proved by testing it through numerous cryptanalysis measurements. We can mention non-linearity, bijectivity, linearity, diferentialcryptanalysis, boomerang attacks resilience, Avalanche efect, and algebraic attacks resilience. The results showthat our proposition provides good resistance to the aforementioned attacks and even shows superiority over its 5-bitcompetitors in terms of non-linearity, diferential, Boomerang, and algebraic attack resistance.
