S M Mehedi Zaman

Megha Chakraborty, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman et al. · apple-ml, stanford

With the rise of prolific ChatGPT, the risk and consequences of AI-generated text has increased alarmingly. To address the inevitable question of ownership attribution for AI-generated artifacts, the US Copyright Office released a statement stating that 'If a work's traditional elements of authorship were produced by a machine, the work lacks human authorship and the Office will not register it'. Furthermore, both the US and the EU governments have recently drafted their initial proposals regarding the regulatory framework for AI. Given this cynosural spotlight on generative AI, AI-generated text detection (AGTD) has emerged as a topic that has already received immediate attention in research, with some initial methods having been proposed, soon followed by emergence of techniques to bypass detection. This paper introduces the Counter Turing Test (CT^2), a benchmark consisting of techniques aiming to offer a comprehensive evaluation of the robustness of existing AGTD techniques. Our empirical findings unequivocally highlight the fragility of the proposed AGTD methods under scrutiny. Amidst the extensive deliberations on policy-making for regulating AI development, it is of utmost importance to assess the detectability of content generated by LLMs. Thus, to establish a quantifiable spectrum facilitating the evaluation and ranking of LLMs according to their detectability levels, we propose the AI Detectability Index (ADI). We conduct a thorough examination of 15 contemporary LLMs, empirically demonstrating that larger LLMs tend to have a higher ADI, indicating they are less detectable compared to smaller LLMs. We firmly believe that ADI holds significant value as a tool for the wider NLP community, with the potential to serve as a rubric in AI-related policy-making.

S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain et al. · apple-ml, stanford

As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of hallucination is arguably the biggest hindrance to safely deploying these powerful LLMs into real-world production systems that impact people's lives. The journey toward widespread adoption of LLMs in practical settings heavily relies on addressing and mitigating hallucinations. Unlike traditional AI systems focused on limited tasks, LLMs have been exposed to vast amounts of online text data during training. While this allows them to display impressive language fluency, it also means they are capable of extrapolating information from the biases in training data, misinterpreting ambiguous prompts, or modifying the information to align superficially with the input. This becomes hugely alarming when we rely on language generation capabilities for sensitive applications, such as summarizing medical records, financial analysis reports, etc. This paper presents a comprehensive survey of over 32 techniques developed to mitigate hallucination in LLMs. Notable among these are Retrieval Augmented Generation (Lewis et al, 2021), Knowledge Retrieval (Varshney et al,2023), CoNLI (Lei et al, 2023), and CoVe (Dhuliawala et al, 2023). Furthermore, we introduce a detailed taxonomy categorizing these methods based on various parameters, such as dataset utilization, common tasks, feedback mechanisms, and retriever types. This classification helps distinguish the diverse approaches specifically designed to tackle hallucination issues in LLMs. Additionally, we analyze the challenges and limitations inherent in these techniques, providing a solid foundation for future research in addressing hallucinations and related phenomena within the realm of LLMs.

S. M Towhidul Islam Tonmoy, S. M Mehedi Zaman

Cyberspace occupies a large portion of people's life in the age of modern technology, and while there are those who utilize it for good, there are also those who do not. Malware is an application whose construction was not motivated by a benign goal and it can harm, steal, or even alter personal information and secure applications and software. Thus, there are numerous techniques to avoid malware, one of which is to develop samples of malware so that the system can be updated with the growing number of malwares, allowing it to recognize when malwares attempt to enter. The Generative Adversarial Network (GAN) sampling technique has been used in this study to generate new malware samples. GANs have multiple variants, and in order to determine which variant is optimal for a given dataset sample, their parameters must be modified. This study employs Optuna, an autonomous hyperparameter tuning algorithm, to determine the optimal settings for the dataset under consideration. In this study, the architecture of the Optuna Optimized GAN (OOG) method is shown, along with scores of 98.06%, 99.00%, 97.23%, and 98.04% for accuracy, precision, recall and f1 score respectively. After tweaking the hyperparameters of five supervised boosting algorithms, XGBoost, LightGBM, CatBoost, Extra Trees Classifier, and Gradient Boosting Classifier, the methodology of this paper additionally employs the weighted ensemble technique to acquire this result. In addition to comparing existing efforts in this domain, the study demonstrates how promising GAN is in comparison to other sampling techniques such as SMOTE.

S. M Mehedi Zaman, Wasay Mahmood Qureshi, Md. Mohsin Sarker Raihan et al.

Cardiovascular disease, especially heart failure is one of the major health hazard issues of our time and is a leading cause of death worldwide. Advancement in data mining techniques using machine learning (ML) models is paving promising prediction approaches. Data mining is the process of converting massive volumes of raw data created by the healthcare institutions into meaningful information that can aid in making predictions and crucial decisions. Collecting various follow-up data from patients who have had heart failures, analyzing those data, and utilizing several ML models to predict the survival possibility of cardiovascular patients is the key aim of this study. Due to the imbalance of the classes in the dataset, Synthetic Minority Oversampling Technique (SMOTE) has been implemented. Two unsupervised models (K-Means and Fuzzy C-Means clustering) and three supervised classifiers (Random Forest, XGBoost and Decision Tree) have been used in our study. After thorough investigation, our results demonstrate a superior performance of the supervised ML algorithms over unsupervised models. Moreover, we designed and propose a supervised stacked ensemble learning model that can achieve an accuracy, precision, recall and F1 score of 99.98%. Our study shows that only certain attributes collected from the patients are imperative to successfully predict the surviving possibility post heart failure, using supervised ML algorithms.