Eleena Sarah Mathew^*

Journal on Artificial Intelligence, Vol.7, pp. 347-363, 2025, DOI:10.32604/jai.2025.069841 - 06 October 2025

Abstract This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations… More >

Sumika Chauhan¹, Govind Vashishtha^1,*, Riya Singh², Divesh Bharti³

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 309-343, 2025, DOI:10.32604/cmes.2025.068628 - 31 July 2025

Abstract This paper introduces a novel optimization approach called Recuperated Seed Search Optimization (RSSO), designed to address challenges in solving mechanical engineering design problems. Many optimization techniques struggle with slow convergence and suboptimal solutions due to complex, nonlinear natures. The Sperm Swarm Optimization (SSO) algorithm, which mimics the sperm’s movement to reach an egg, is one such technique. To improve SSO, researchers combined it with three strategies: opposition-based learning (OBL), Cauchy mutation (CM), and position clamping. OBL introduces diversity to SSO by exploring opposite solutions, speeding up convergence. CM enhances both exploration and exploitation capabilities throughout More >

Tareq Hamadneh¹, Belal Batiha², Omar Alsayyed³, Widi Aribowo⁴, Zeinab Montazeri⁵, Mohammad Dehghani^5,*, Frank Werner^6,*, Haider Ali⁷, Riyadh Kareem Jawad⁸, Ibraheem Kasim Ibraheem⁹, Kei Eguchi¹⁰

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2677-2718, 2025, DOI:10.32604/cmc.2025.064087 - 16 April 2025

Abstract In this study, a completely different approach to optimization is introduced through the development of a novel metaheuristic algorithm called the Barber Optimization Algorithm (BaOA). Inspired by the human interactions between barbers and customers, BaOA captures two key processes: the customer’s selection of a hairstyle and the detailed refinement during the haircut. These processes are translated into a mathematical framework that forms the foundation of BaOA, consisting of two critical phases: exploration, representing the creative selection process, and exploitation, which focuses on refining details for optimization. The performance of BaOA is evaluated using 52 standard… More >

Robertas Damasevicius^*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 1493-1538, 2025, DOI:10.32604/cmc.2024.057431 - 17 February 2025

Abstract Heuristic optimization algorithms have been widely used in solving complex optimization problems in various fields such as engineering, economics, and computer science. These algorithms are designed to find high-quality solutions efficiently by balancing exploration of the search space and exploitation of promising solutions. While heuristic optimization algorithms vary in their specific details, they often exhibit common patterns that are essential to their effectiveness. This paper aims to analyze and explore common patterns in heuristic optimization algorithms. Through a comprehensive review of the literature, we identify the patterns that are commonly observed in these algorithms, including… More >

Tareq Hamadneh¹, Belal Batiha², Omar Alsayyed³, Frank Werner^4,*, Zeinab Monrazeri⁵, Mohammad Dehghani^5,*, Kei Eguchi⁶

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 2253-2323, 2024, DOI:10.32604/cmes.2024.055171 - 31 October 2024

Abstract This paper introduces the Wolverine Optimization Algorithm (WoOA), a biomimetic method inspired by the foraging behaviors of wolverines in their natural habitats. WoOA innovatively integrates two primary strategies: scavenging and hunting, mirroring the wolverine’s adeptness in locating carrion and pursuing live prey. The algorithm’s uniqueness lies in its faithful simulation of these dual strategies, which are mathematically structured to optimize various types of problems effectively. The effectiveness of WoOA is rigorously evaluated using the Congress on Evolutionary Computation (CEC) 2017 test suite across dimensions of 10, 30, 50, and 100. The results showcase WoOA’s robust… More >

Qianqian Zhang¹, Yingmei Li^1,*, Jianjun Zhan^2,*, Shan Chen¹

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 1251-1273, 2024, DOI:10.32604/cmc.2024.053892 - 15 October 2024

Abstract This research focuses on improving the Harris’ Hawks Optimization algorithm (HHO) by tackling several of its shortcomings, including insufficient population diversity, an imbalance in exploration vs. exploitation, and a lack of thorough exploitation depth. To tackle these shortcomings, it proposes enhancements from three distinct perspectives: an initialization technique for populations grounded in opposition-based learning, a strategy for updating escape energy factors to improve the equilibrium between exploitation and exploration, and a comprehensive exploitation approach that utilizes variable neighborhood search along with mutation operators. The effectiveness of the Improved Harris Hawks Optimization algorithm (IHHO) is assessed by… More >

Tareq Hamadneh^1,2, Khalid Kaabneh³, Omar Alssayed⁴, Kei Eguchi^5,*, Zeinab Monrazeri⁶, Mohammad Dehghani⁶

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.2, pp. 1725-1808, 2024, DOI:10.32604/cmes.2024.053236 - 27 September 2024

Abstract In this article, a novel metaheuristic technique named Far and Near Optimization (FNO) is introduced, offering versatile applications across various scientific domains for optimization tasks. The core concept behind FNO lies in integrating global and local search methodologies to update the algorithm population within the problem-solving space based on moving each member to the farthest and nearest member to itself. The paper delineates the theory of FNO, presenting a mathematical model in two phases: (i) exploration based on the simulation of the movement of a population member towards the farthest member from itself and (ii)… More >

Tareq Hamadneh¹, Khalid Kaabneh², Ibraheem AbuFalahah³, Gulnara Bektemyssova^4,*, Galymzhan Shaikemelev⁴, Dauren Umutkulov⁴, Sayan Omarov⁵, Zeinab Monrazeri⁶, Frank Werner⁷, Mohammad Dehghani^6,*

CMC-Computers, Materials & Continua, Vol.80, No.2, pp. 2721-2741, 2024, DOI:10.32604/cmc.2024.054317 - 15 August 2024

Abstract This paper introduces a groundbreaking metaheuristic algorithm named Magnificent Frigatebird Optimization (MFO), inspired by the unique behaviors observed in magnificent frigatebirds in their natural habitats. The foundation of MFO is based on the kleptoparasitic behavior of these birds, where they steal prey from other seabirds. In this process, a magnificent frigatebird targets a food-carrying seabird, aggressively pecking at it until the seabird drops its prey. The frigatebird then swiftly dives to capture the abandoned prey before it falls into the water. The theoretical framework of MFO is thoroughly detailed and mathematically represented, mimicking the frigatebird’s… More >

Guochen Xu^*

FDMP-Fluid Dynamics & Materials Processing, Vol.20, No.8, pp. 1915-1924, 2024, DOI:10.32604/fdmp.2024.048337 - 06 August 2024

Abstract Microscopic pore structure in continental shale oil reservoirs is characterized by small pore throats and complex micro-structures. The adsorption behavior of hydrocarbons on the pore walls exhibits unique physical and chemical properties. Therefore, studying the adsorption morphology of hydrocarbon components in nanometer-sized pores and clarifying the exploitation limits of shale oil at the microscopic level are of great practical significance for the efficient development of continental shale oil. In this study, molecular dynamics simulations were employed to investigate the adsorption characteristics of various single-component shale oils in inorganic quartz fissures, and the influence of pore… More >

Ibraheem Abu Falahah¹, Osama Al-Baik², Saleh Alomari³, Gulnara Bektemyssova⁴, Saikat Gochhait^5,6, Irina Leonova⁷, Om Parkash Malik⁸, Frank Werner^9,*, Mohammad Dehghani¹⁰

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 3631-3678, 2024, DOI:10.32604/cmc.2024.053189 - 20 June 2024

Abstract This research presents a novel nature-inspired metaheuristic algorithm called Frilled Lizard Optimization (FLO), which emulates the unique hunting behavior of frilled lizards in their natural habitat. FLO draws its inspiration from the sit-and-wait hunting strategy of these lizards. The algorithm’s core principles are meticulously detailed and mathematically structured into two distinct phases: (i) an exploration phase, which mimics the lizard’s sudden attack on its prey, and (ii) an exploitation phase, which simulates the lizard’s retreat to the treetops after feeding. To assess FLO’s efficacy in addressing optimization problems, its performance is rigorously tested on fifty-two… More >