With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology. Meanwhile, various vulnerabilities in smart contracts have been exploited by attackers to steal cryptocurrencies worth millions of dollars. The automatic detection of smart contract vulnerabilities therefore is an essential research problem. Existing solutions to this problem particularly rely on human experts to define features or different rules to detect vulnerabilities. However, this often causes many vulnerabilities to be ignored, and they are inefficient in detecting new vulnerabilities. In this study, to overcome such challenges, we propose a framework to automatically detect vulnerabilities in smart contracts on the blockchain. More specifically, first, we utilize novel feature vector generation techniques from bytecode of smart contract as source code is rarely publicly available. These feature vectors are then analyzed using our innovative metric learning-based Deep Neural Networks (DNNs) to produce detection results. The framework’s predictions are further refined through a voting mechanism to achieve consensus. We conduct comprehensive experiments on large-scale benchmarks, and the quantitative results demonstrate the effectiveness and efficiency of our approach.

In real-world applications, data-driven classifiers often grapple with a three-pronged challenge: data arrives in a continuous stream, most data in the wild are often unlabeled, and there is a critical need to maintain fairness in predictions across different sub-groups. Existing methods falter when addressing all these three factors concurrently. This work tackles this challenge by addressing a novel paradigm: Fairness-Aware Active Online Learning. We introduce a simple yet effective approach - FACTION, which actively selects the most crucial data points for labeling, going beyond traditional methods by considering both model uncertainty (epistemic uncertainty) and a newly introduced fairness notion derived from this very uncertainty. Additionally, FACTION leverages a system adept at identifying out-of-distribution samples within online learning environ-ments. Extensive evaluations on real-world datasets, coupled with theoretical analysis, demonstrate FACTION's effectiveness in handling this complex challenge. Our model demonstrably outperforms relevant baselines adapted for this new setting.

Machine learning models increasingly influence decisions in high-stakes settings such as finance, law and hiring, driving the need for transparent, interpretable outcomes. However, while explainable approaches can help understand the decisions being made, they may inadvertently reveal the underlying proprietary algorithm—an undesirable outcome for many practitioners. Consequently, it is crucial to balance meaningful transparency with a form of recourse that clarifies why a decision was made and offers actionable steps following which a favorable outcome can be obtained. Counterfactual explanations offer a powerful mechanism to address this need by showing how specific input changes lead to a more favorable prediction. We propose Model-Agnostic Causally Constrained Counterfactual Generation (MC3G), a novel framework that tackles limitations in the existing counterfactual methods. First, MC3G is model-agnostic: it approximates any black-box model using an explainable rule-based surrogate model. Second, this surrogate is used to generate counterfactuals that produce a favourable outcome for the original underlying black box model. Third, MC3G refines cost computation by excluding the “effort” associated with feature changes that occur automatically due to causal dependencies. By focusing only on user-initiated changes, MC3G provides a more realistic and fair representation of the effort needed to achieve a favourable outcome. We show that MC3G delivers more interpretable and actionable counterfactual recommendations compared to existing techniques all while having a lower cost. Our findings highlight MC3G’s potential to enhance transparency, accountability, and practical utility in decision-making processes that incorporate machine-learning approaches.

Traditional machine learning relies on centralized data, which poses risks to privacy and strains networks when collecting data from multiple centers. Federated Learning, introduced to address these challenges, trains models on various clients, transfers them to a central server to aggregate their knowledge in a global model, and shares the global model with clients to transfer knowledge among them. In real-world problems, data are not distributed independently and identically among different data sources. The non-IID nature of data makes the learning process more challenging, especially when the problem is non-convex. In such cases, the global model may become trapped in local optima. In this paper, we have introduced an approach that employs techniques from metaheuristic optimization algorithms to help the learning process escape from local optima. Relying on the concepts of exploration and exploitation, the optimization process is directed toward promising areas. Experiments conducted on several non-IID datasets show that our algorithm outperforms others in a wide variety of cases.

The spread of attacks in computer networks and within systems can have severe consequences for both individuals and organizations. One approach to preventing the spread of attacks is to use ontological aid, which is the use of ontologies to provide a structured representation of knowledge about the attack and its components, especially the ones who often disguise themselves to remain undetected for a long time within the system. As soon as one particular stage of such an attack is detected, it is imperative to reduce the amount of spread so that no permanent damage can be done. For this, the security analyst must boil down to technical details from a behavioral perspective so that proper defensive initiatives can be taken. We propose an ontology that will aid security analysts to find out the list of vulnerabilities to be patched so that an ongoing attack campaign can be prevented from spreading even more.

With hate speech spreading rapidly online, it is increasingly important to respond automatically. However, there are some critical limitations in developing systems which produce these responses, which are known as counterspeeches. First, datasets containing paired instances of a hate speech and its appropriate response are very small. There is an abundance of hate speech on the web and in structured datasets, but quality counterspeeches are rare. Thus, since data is scarce, there is a need for automated methods to intelligently increase the size of existing paired datasets. Another critical challenge is that existing Natural Language Generation (NLG) metrics are not suitable for evaluating such systems, because these metrics do not accurately reflect how a human interprets the relationship between a hate speech and its counterspeech. Lastly, language models trained on internet text often exhibit a large amount of bias, which is unsuitable for sensitive tasks such as counterspeech generation. To address these challenges, we first introduce a technique to intelligently augment a small paired dataset of hate speech and counterspeech to make it substantially larger and varied, through a pairing technique that appropriately matches unpaired instances of hate speech with synthetic and existing counterspeeches. Next, we identified a need for a metric that evaluates counterspeech in the same way humans do, and propose a novel metric called PD-Score that leverages an advanced debating system. We empirically show through a large survey, that existing NLG metrics correlate poorly to human assessment and that our alternative is much more tightly bound to human assessment. Lastly, we curated a large domain-specific text corpus called WokeCorpus which we use to pretrain the language model before finetuning it for producing counterspeeches. We show that this both debiases the language model and aids performance.