Recent advances in synthetic data generation have enabled high-fidelity modeling of tabular datasets, yet fairness remains a peripheral concern, often addressed through architectural modifications or fairness-aware loss functions. We introduce CondFairGen, a fairness-aware generative model that enforces group fairness through dynamic control of conditional exposure during training. Rather than altering the model architecture or objective, CondFairGen reweights the sampling distribution over conditioning vectors based on disparity metrics across protected attributes and their intersections. This reweighting increases exposure to underrepresented or high-disparity subgroups, guiding the model toward fairer conditional distributions. By embedding fairness directly into the training schedule, CondFairGen offers a principled alternative to adversarial debiasing or post hoc correction. Empirical evaluations on standard tabular benchmarks demonstrate that CondFairGen substantially improves both marginal and intersectional fairness metrics while preserving downstream utility. These results establish conditional exposure as a practical and effective mechanism for fairness intervention in generative modeling.

The widespread use of big data across various sectors has brought significant privacy concerns, particularly when sensitive information is shared or analyzed. Regulations like GDPR and HIPAA impose strict controls on handling data, making it difficult to balance the need for insights with privacy requirements. Synthetic data offers a promising solution, enabling the creation of artificial datasets that mirror real-world patterns without exposing sensitive information. For instance, synthetic data can simulate patient records or network flows for training machine learning models to conduct research without violating privacy laws. However, traditional synthetic data generation methods often fail to capture complex, implicit rules that relate different elements of the data and are essential in specific domains like healthcare. While these methods might replicate explicit patterns from the training data, they often overlook domain-specific rules that are not directly stated but are critical for maintaining realism and utility. For example, prescription guidelines, such as avoiding certain medications for patients with specific conditions or preventing harmful drug interactions, may not be explicitly represented in the original data. Synthetic data generated without accounting for these implicit rules can lead to medically inappropriate or unrealistic patient profiles. To address these limitations, we propose a framework called Context-Aware Differentially Private Generative Adversarial Network (ContextGAN). Our framework integrates domain-specific rules using a constraint matrix that explicitly encodes both explicit and implicit domain knowledge. The constraint-aware discriminator evaluates synthetic data against these rules, ensuring the generated data adheres to domain constraints. Furthermore, the discriminator is differentially private, ensuring privacy preservation by protecting sensitive details from the original data. We validate ContextGAN across multiple domains, including healthcare, security, and finance, demonstrating that it produces high-quality synthetic data that respects domain-specific rules while preserving privacy. Our results show that ContextGAN significantly improves the realism and utility of synthetic data by enforcing domain constraints, making it suitable for use in scenarios requiring both compliance with explicit patterns and implicit rules, all under strict privacy guarantees.

Big Data empowers the farming community with the information needed to optimize resource usage, increase productivity, and enhance the sustainability of agricultural practices. The use of Big Data in farming requires the collection and analysis of data from various sources such as sensors, satellites, and farmer surveys. While Big Data can provide the farming community with valuable insights and improve efficiency, there is significant concern regarding the security of this data as well as the privacy of the participants. Privacy regulations, such as the European Union’s General Data Protection Regulation (GDPR), the EU Code of Conduct on agricultural data sharing by contractual agreement, and the proposed EU AI law, have been created to address the issue of data privacy and provide specific guidelines on when and how data can be shared between organizations. To make confidential agricultural data widely available for Big Data analysis without violating the privacy of the data subjects, we consider privacy-preserving methods of data sharing in agriculture. Synthetic data that retains the statistical properties of the original data but does not include actual individuals’ information provides a suitable alternative to sharing sensitive datasets. Deep learning-based synthetic data generation has been proposed for privacy-preserving data sharing. However, there is a lack of compliance with documented data privacy policies in such privacy-preserving efforts. In this study, we propose a novel framework for enforcing privacy policy rules in privacy-preserving data generation algorithms. We explore several available agricultural codes of conduct, extract knowledge related to the privacy constraints in data, and use the extracted knowledge to define privacy bounds in a privacy-preserving generative model. We use our framework to generate synthetic agricultural data and present experimental results that demonstrate the utility of the synthetic dataset in downstream tasks. We also show that our framework can evade potential threats, such as re-identification and linkage issues, and secure data based on applicable regulatory policy rules.

Named Entity Recognition (NER) is important in the cybersecurity domain. It helps researchers extract cyber threat information from unstructured text sources. The extracted cyber-entities or key expressions can be used to model a cyber-attack described in an open-source text. A large number of general-purpose NER algorithms have been published that work well in text analysis. These algorithms do not perform well when applied to the cybersecurity domain. In the field of cybersecurity, the open-source text available varies greatly in complexity and under-lying structure of the sentences. General-purpose NER algorithms can misrepresent domain-specific words, such as "malicious" and "javascript". In this paper, we compare the recent deep learning-based NER algorithms on a cybersecurity dataset. We created a cybersecurity dataset collected from various sources, including "Microsoft Security Bulletin" and "Adobe Security Updates". Some of these approaches proposed in literature were not used for Cybersecurity. Others are innovations proposed by us. This comparative study helps us identify the NER algorithms that are robust and can work well in sentences taken from a large number of cybersecurity sources. We tabulate their performance on the test set and identify the best NER algorithm for a cybersecurity corpus. We also discuss the different embedding strategies that aid in the process of NER for the chosen deep learning algorithms.

Data protection authorities formulate policies and rules which the service providers have to comply with to ensure security and privacy when they perform Big Data analytics using users Personally Identifiable Information (PII). The knowledge contained in the data regulations and organizational privacy policies are typically maintained as short unstructured text in HTML or PDF formats. Hence it is an open challenge to determine the specific regulation rules that are being addressed by a provider's privacy policies. We have developed a semantically rich framework, using techniques from Semantic Web and Natural Language Processing, to extract and compare the context of a short text in real-time. This framework allows automated incremental text comparison and identifying context from short text policy documents by determining the semantic similarity score and extracting semantically similar key terms. Additionally, we also created a knowledge graph to store the semantically similar comparison results while evaluating our framework across EU GDPR and privacy policies of 20 organizations complying with this regulation associated with various categories apply to Big Data stored in the cloud. Our approach can be utilized by Big Data practitioners to update their referential documents regularly based on the authority documents.

Machine learning algorithms used to detect attacks are limited by the fact that they cannot incorporate the back-ground knowledge that an analyst has. This limits their suitability in detecting new attacks. Reinforcement learning is different from traditional machine learning algorithms used in the cybersecurity domain. Compared to traditional ML algorithms, reinforcement learning does not need a mapping of the input-output space or a specific user-defined metric to compare data points. This is important for the cybersecurity domain, especially for malware detection and mitigation, as not all problems have a single, known, correct answer. Often, security researchers have to resort to guided trial and error to understand the presence of a malware and mitigate it.In this paper, we incorporate prior knowledge, represented as Cybersecurity Knowledge Graphs (CKGs), to guide the exploration of an RL algorithm to detect malware. CKGs capture semantic relationships between cyber-entities, including that mined from open source. Instead of trying out random guesses and observing the change in the environment, we aim to take the help of verified knowledge about cyber-attack to guide our reinforcement learning algorithm to effectively identify ways to detect the presence of malicious filenames so that they can be deleted to mitigate a cyber-attack. We show that such a guided system outperforms a base RL system in detecting malware.