Automated asset management based on partially cooperative agents for a world of risks

Castro, Paulo André Lima de; Sichman, Jaime Simão

doi:10.1007/s10489-012-0366-8

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A MAS defnes the roles that an agent can adopt and the tasks associated with each role. Furthermore, it also defnes how agents communicate among themselves and deal with confict resolution such as negotiation among agents (see [14]) or based on a pre-defned division of work. The MADEX architecture is an example of the latter case.…”

Section: Madexmentioning

confidence: 99%

A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks

Marques

Epiphaniou

Al-Khateeb

et al. 2021

ACM Trans. Internet Technol.

Self Cite

View full text Add to dashboard Cite

Modern network infrastructures host converged applications that demand rapid elasticity of services, increased security, and ultra-fast reaction times. The Tactile Internet promises to facilitate the delivery of these services while enabling new economies of scale for high fidelity of machine-to-machine and human-to-machine interactions. Unavoidably, critical mission systems served by the Tactile Internet manifest high demands not only for high speed and reliable communications but equally, the ability to rapidly identify and mitigate threats and vulnerabilities. This article proposes a novel Multi-Agent Data Exfiltration Detector Architecture (MADEX), inspired by the mechanisms and features present in the human immune system. MADEX seeks to identify data exfiltration activities performed by evasive and stealthy malware that hides malicious traffic from an infected host in low-latency networks. Our approach uses cross-network traffic information collected by agents to effectively identify unknown illicit connections by an operating system subverted. MADEX does not require prior knowledge of the characteristics or behavior of the malicious code or a dedicated access to a knowledge repository. We tested the performance of MADEX in terms of its capacity to handle real-time data and the sensitivity of our algorithm’s classification when exposed to malicious traffic. Experimental evaluation results show that MADEX achieved 99.97% sensitivity, 98.78% accuracy, and an error rate of 1.21% when compared to its best rivals. We created a second version of MADEX, called MADEX level 2, that further improves its overall performance with a slight increase in computational complexity. We argue for the suitability of MADEX level 1 in non-critical environments, while MADEX level 2 can be used to avoid data exfiltration in critical mission systems. To the best of our knowledge, this is the first article in the literature that addresses the detection of rootkits real-time in an agnostic way using an artificial immune system approach while it satisfies strict latency requirements.

show abstract

Section: Madexmentioning

confidence: 99%

A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks

Marques

Epiphaniou

Al-Khateeb

et al. 2021

ACM Trans. Internet Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Podem ser citados vários exemplos de estratégias ou indicadores de análise técnica, como indicador Sthocastic,índice de força relativa (IFR), Price Oscillator, Moving Average, Moving Average Convergence/Divergence (MACD), Teoria das Ondas de Elliott, Accumulation/Distribution Index, indicador Momentum entre outros [13,14].…”

Section: Análise Técnicaunclassified

“…Por exemplo, classificá-los de acordo com a principal técnica de inteligência artificial utilizada: redes neurais [17],deep learning [18], aprendizado por reforço [19,20], sistemas multiagentes [21,22,14], arquiteturas BDI [23], raciocínio baseado em casos [24], inteligência de enxame (SWARM) [25], etc. Outra classificação possível seria a capacidade de trabalhar como vários ativos simultaneamente (multi-ativo) ou com apenas um ativo (monoativo).…”

Section: Trabalhos Relacionados a Análise Autônoma De Ativosunclassified

“…Pode-se perceber uma predominância do grupo mono-ativo. A razão deste fato, torna-se mais clara ao se agrupar os trabalhos em relação aos objetivos do agente (ou da sociedade multiagentes): maximização de retorno [21,22,26,24,27,19,17,20,23], minimização de risco (sem trabalhos conhecidos) ou uma solução de compromisso entre risco e retorno [25,14].…”

Section: Trabalhos Relacionados a Análise Autônoma De Ativosunclassified

See 1 more Smart Citation

Análise Autônoma de Investimento: Uma Abordagem Multiagente Discreta

Castro

Annoni²,

Sichman

2018

RITA

Self Cite

View full text Add to dashboard Cite

Since early days of computer science, researchers ask themselves where is the line that separates tasks machine can do from those only human beings can really accomplish. Several tasks were pointed as impossible to machines and later conquered by new advances in Artificial Intelligence. Nowadays, it seems we are not far from the day when driving cars will be included among the tasks machines can do in an efficient way. Certainly, even more complex activities will be dominated by machines in the future. In fact, there is significant research effort to make investment analysis become one those activities. In this paper, we propose a probabilistic approach for autonomous investment analysis (AIA) that deals with three dimensions of complexity (nature of assets, multiple analysis algorithms per asset and horizon of investment, non-stationary nature of the environment). This approach is based in multiple autonomous agents, discretization of AIA problem and its modelling as a classification problem. This approach breaks down the complexity faced by AIA in problems that can be addressed by a group of agents that work together to provide intelligent and customized investment advices for individuals. We present an implementation of such approach and the results achieved by using it will historic data from Brazilian stock market. We believe that such approach may contribute to development of AIA. Furthermore, this approach allows an easy integration with algorithms and techniques already developed, that may help to solve part of the problem. Keywords: autonomous investment analysis -artificial intelligence -online learningResumo: Desde os primeiros dias da ciência da computação, os pesquisadores se perguntam onde está a linha que separa as tarefas que máquinas podem fazer, daquelas que apenas seres humanos podem realizar. Várias tarefas foram apontadas como impossíveis para as máquinas e mais tarde conquistadas por novos avanços na Inteligência Artificial. Hoje em dia, parece que não estamos longe do dia em que a condução de carros será incluída nas tarefas que as máquinas podem fazer de maneira eficiente. Certamente, atividades ainda mais complexas serão dominadas por máquinas no futuro. Na verdade, há esforços de pesquisa significativos para tornar análise de investimento uma dessas atividades. Neste artigo, propomos uma abordagem probabilística para análise autônoma de investimentos (AAI) capaz de lidar com três dimensões de complexidade (natureza dos ativos, algoritmos de análise múltipla por ativo, não estacionaridade e múltiplos horizonte de investimento). Esta abordagem baseia-se no uso simultâneo de diversos agentes autônomos e na discretização do problema AAI e sua modelagem como um problema de classificação. Essa abordagem quebra a complexidade enfrentada pela AAI em problemas que podem ser abordados por um grupo de agentes que trabalham em conjunto para fornecer conselhos de investimento inteligentes e personalizados para indivíduos. Apresentamos uma implementação dessa abordagem e resultados obtidos ...

show abstract

“…pp. 212-213, [4]). They can be seen as Expected Utility Theory (EUT) strategies, because they are not concerned in reproducing human behavior but maximizing some value (or utility).…”

Section: Tra Agentsmentioning

confidence: 99%

Expected utility or prospect theory: Which better fits agent-based modeling of markets?

Castro

Teodoro

Castro

et al. 2016

Journal of Computational Science

Self Cite

View full text Add to dashboard Cite

show abstract

Automated asset management based on partially cooperative agents for a world of risks

Cited by 6 publications

References 14 publications

A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks

A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks

Análise Autônoma de Investimento: Uma Abordagem Multiagente Discreta

Expected utility or prospect theory: Which better fits agent-based modeling of markets?

Contact Info

Product

Resources

About