JDJaqueline Damacena Duarte

Jaqueline Damacena Duarte

*This is an algorithmically generated author record based on publicly available information.

Jaqueline Damacena Duarte has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Detecção de Mensagens de Phishing Geradas por Modelos Generativos de Linguagem em Português por Meio de Atributos Estilométricos Resilientes a Vieses de Geração Sintética

    by Jeanderson Medeiros da Silva, Jaqueline Damacena Duarte, Fabio Lucio Lopes de Mendonca, Laerte Peotta de Melo

    Este artigo investiga o potencial de um modelo preditivo baseado em estilometria comportamental para identificar phishing gerado por IA em Português. A metodologia foca na extração de atributos morfológicos, como comandos imperativos, para mitigar vieses de modelos sintéticos. Diante do cenário de dataset shift entre arquiteturas (Gemini e GPT-4o), avaliou-se um classificador XGBoost que alcançou F1-Score de 0,91 em ambiente controlado. Os resultados indicam que a análise estilométrica oferece indícios relevantes para complementar defesas tradicionais, embora a generalização em cenários reais ainda demande validação com dados orgânicos.

  • Top Cited Papers
    Open Access

    A Systematic Review of Prompt Injection Attacks on Large Language Models: Trends, Taxonomy, Evaluation, Defenses, and Opportunities

    by Jaqueline Damacena Duarte, Guilherme D. Cândido, José Ricardo A. De Britto Filho, João Souza Neto, Elena J. Da Costa, João Paulo Javidi Da Costa, Laerte Peotta De Melo

    Large Language Models (LLMs) are increasingly integrated into various infrastructure and interactive applications. However, their inherent linguistic flexibility introduces security vulnerabilities, particularly through Prompt Injection (PI) attacks. This systematic review provides a comprehensive synthesis of the evolving landscape of PI attacks, including their development trends, classification schemes, evaluation methodologies, defense strategies, and areas for future research. We analyze the evolution of attacks from basic natural language overrides to complex multi-turn manipulations, indirect injections using structured formats such as JSON and XML, and tool-assisted exploits involving automated prompt generation and multi-modal inputs like images. PI attacks are categorized by the level of manipulation, including character, word, sentence, and semantic levels, and by adversarial intent, such as prompt leaking and harmful content generation. The study analyzes these techniques within different LLM architectures and application contexts, including machine translation and Chain of Thought reasoning. It also reviews common evaluation benchmarks, datasets, and metrics. Mitigation strategies examined include automated red teaming frameworks, input validation, content filtering, and alignment through training. It differentiates itself from previous works by conducting a systematic review specifically focused on immediate injection, organizing its attacks, defenses and research gaps. Finally, this review identifies major research challenges and suggests critical directions for improving LLM safety and robustness.


  • Open Access

    AI-driven modern slavery detection for supply chain: A cross-jurisdictional legal text analysis

    by Jaqueline Damacena Duarte, Elena Javidi da Costa, Joao Paulo Javidi da Costa, Ana Sofia Schweizer Silvestre, Edna Dias Canedo, Hernany Silveira Rocha


  • Open Access

    A New Dataset and Neural Benchmark for Multi-Label Classification of Modern Slavery Litigation

    by Hernany S. Rocha, Elena J. Da Costa, Jaqueline D. Duarte, João Paulo J. Da Costa

    Modern slavery remains a critical global challenge, affecting millions of individuals through forced labor and human trafficking. As global supply chains become increasingly complex, corporations face growing legal, financial, and reputational risks related to human rights violations. Ensuring transparency and compliance with regulations such as the UK Modern Slavery Act 2015 has become essential, yet progress is hindered by the lack of any available, domain-specific datasets that enable automated monitoring of legal cases. To address this gap, we introduce the Modern Slavery Supply-Chain Cases (MOSSC) dataset, the first resource designed for multi-label text classification (MLTC) of modern slavery litigation. MOSSC contains 1,882 United Kingdom (UK) court judgments from 2015 to 2025, meticulously annotated with 329 fine-grained legal and factual labels relevant to human rights and supply chain compliance. We perform a comprehensive benchmarking study evaluating ten neural architectures, ranging from Bidirectional Gated Recurrent Units (BiGRU) to domain-adapted Bidirectional Encoder Representations from Transformers (BERT) models, including BERT-ECHR pre-trained on European Court of Human Rights cases. Our results demonstrate that BERT-ECHR achieves the highest performance, with a R-Precision at rank 2 (RP@2) of 0.8830 and a normalized Discounted Cumulative Gain at rank 2 (nDCG@2) of 0.8682. In addition, a lightweight BiGRU combined with Law2Vec embeddings offers an efficient alternative for resource-constrained applications. By providing MOSSC along with trained models and open-source code, we enable the development of artificial intelligence (AI)-driven tools for automated monitoring of supply chain risks. This approach empowers companies, auditors, and regulators to detect patterns of exploitation more effectively, assess legal exposure, and enhance compliance with environmental, social, and governance (ESG) requirements. Our work establishes the first robust baselines for AI-driven legal analytics in this domain, paving the way for greater transparency and ethical practices across global supply chains.


  • Open Access

    Machine Learning for Early Detection of Phishing URLs in Parked Domains: An Approach Applied to a Financial Institution

    by Jaqueline D. Duarte, Pedro Chagas Junior, João Paulo Javidi da Costa, Elena J. da Costa, Laerte Peotta de Melo, Rafael Rabelo Nunes, Carlos V. N. Gabriel Soares, Thiago Erivan da Cunha Silva

    Phishing attacks remain a critical threat in the digital era, exploiting social engineering tactics to compromise user trust and sensitive information, often resulting in financial loss and identity theft. These attacks typically exploit multiple communication channels to impersonate trusted entities, inducing users to click on and access malicious Resource Locations (URLs). Early detection of these URLs can considerably reduce the volume and impact of these attacks. This paper proposes a machine learning-based framework for early detection of phishing URLs, specifically addressing newly registered and parked domains. Using a curated dataset comprising 211,659 URLs obtained from real-time SSL (Secure Sockets Layer) certificate monitoring, popular domain listings, and phishing incident reports, the methods encompass data pre-processing, feature engineering, and model optimization. A Light Gradient Boosting Machine classifier achieved recall of 96.02% and accuracy of 97.28% on a balanced dataset, validated through 10-fold cross-validation. Additionally, feature selection techniques reduced model complexity while maintaining detection effectiveness, facilitating practical deployment. The proposed frameworks provide a versatile tool for phishing prevention and brand protection, demonstrating potential applicability in sectors such as banking and e-commerce. This work contributes to proactive cybersecurity practices addressing evolving threats within digital ecosystems.


  • Open Access

    Synthetic Minority Over-sampling Technique for detecting Malicious Traffic targeting Internet of Things' devices

    by Jaqueline Damacena Duarte, Guilherme Dantas Bispo, Gabriel Arquelau Pimenta Rodrigues, André Luiz Marques Serrano, Gabriela Mayumi Saiki, Vinícius Pereira Gonçalves

    This study proposes a multiclass machine learning approach for detecting 34 distinct types of cyberattacks in Internet of Things (IoT) traffic using the CICIoT2023 dataset. We evaluate the performance of lightweight classifiers—Bernoulli Naive Bayes, Decision Tree, Random Forest, and XGBoost—under highly imbalanced conditions. To address class imbalance and improve minority-class detection, we apply the Synthetic Minority Over-sampling Technique (SMOTE). In addition, we conduct hyperparameter tuning using RandomizedSearchCV and assess model performance using macro-average metrics, including recall, precision, and F1-score. Experimental results demonstrate that XGBoost and Random Forest, when optimized and combined with SMOTE, consistently achieves high and balanced detection rates across all classes. These findings suggest its applicability to real-world IoT intrusion detection scenarios, particularly in resource-constrained environments.