Muhammad Rafi

Farhan Dhanani, Muhammad Rafi

This paper presents solutions to the Machine Learning Model Attribution challenge (MLMAC) collectively organized by MITRE, Microsoft, Schmidt-Futures, Robust-Intelligence, Lincoln-Network, and Huggingface community. The challenge provides twelve open-sourced base versions of popular language models developed by well-known organizations and twelve fine-tuned language models for text generation. The names and architecture details of fine-tuned models were kept hidden, and participants can access these models only through the rest APIs developed by the organizers. Given these constraints, the goal of the contest is to identify which fine-tuned models originated from which base model. To solve this challenge, we have assumed that fine-tuned models and their corresponding base versions must share a similar vocabulary set with a matching syntactical writing style that resonates in their generated outputs. Our strategy is to develop a set of queries to interrogate base and fine-tuned models. And then perform one-to-many pairing between them based on similarities in their generated responses, where more than one fine-tuned model can pair with a base model but not vice-versa. We have employed four distinct approaches for measuring the resemblance between the responses generated from the models of both sets. The first approach uses evaluation metrics of the machine translation, and the second uses a vector space model. The third approach uses state-of-the-art multi-class text classification, Transformer models. Lastly, the fourth approach uses a set of Transformer based binary text classifiers, one for each provided base model, to perform multi-class text classification in a one-vs-all fashion. This paper reports implementation details, comparison, and experimental studies, of these approaches along with the final obtained results.

Murad Popattia, Muhammad Rafi, Rizwan Qureshi et al.

The use of attention models for automated image captioning has enabled many systems to produce accurate and meaningful descriptions for images. Over the years, many novel approaches have been proposed to enhance the attention process using different feature representations. In this paper, we extend this approach by creating a guided attention network mechanism, that exploits the relationship between the visual scene and text-descriptions using spatial features from the image, high-level information from the topics, and temporal context from caption generation, which are embedded together in an ordered embedding space. A pairwise ranking objective is used for training this embedding space which allows similar images, topics and captions in the shared semantic space to maintain a partial order in the visual-semantic hierarchy and hence, helps the model to produce more visually accurate captions. The experimental results based on MSCOCO dataset shows the competitiveness of our approach, with many state-of-the-art models on various evaluation metrics.

Michael Cahyadi, Muhammad Rafi, William Shan et al.

We qualitatively examine the accuracy and fidelity between two diffusion-based image generation systems, namely DALL-E 2 and Luna, which have massive differences in training datasets, algorithmic approaches, prompt resolvement, and output upscaling. The methodology used is a qualitative benchmark created by Saharia et al. and in our research we conclude that DALL-E 2 significantly edges Luna in both alignment and fidelity comparisons.

Behraj Khan, Tahir Syed, Zeshan Khan et al.

New software and updates are downloaded by end users every day. Each dowloaded software has associated with it an End Users License Agreements (EULA), but this is rarely read. An EULA includes information to avoid legal repercussions. However,this proposes a host of potential problems such as spyware or producing an unwanted affect in the target system. End users do not read these EULA's because of length of the document and users find it extremely difficult to understand. Text summarization is one of the relevant solution to these kind of problems. This require a solution which can summarize the EULA and classify the EULA as "Benign" or "Malicious". We propose a solution in which we have summarize the EULA and classify the EULA as "Benign" or "Malicious". We extract EULA text of different sofware's then we classify the text using eight different supervised classifiers. we use ensemble learning to classify the EULA as benign or malicious using five different text summarization methods. An accuracy of $95.8$\% shows the effectiveness of the presented approach.

Ali Zain, Sareem Farooqui, Muhammad Rafi

This paper details our submission to the AraGenEval Shared Task on Arabic AI-generated text detection, where our team, BUSTED, secured 5th place. We investigated the effectiveness of three pre-trained transformer models: AraELECTRA, CAMeLBERT, and XLM-RoBERTa. Our approach involved fine-tuning each model on the provided dataset for a binary classification task. Our findings revealed a surprising result: the multilingual XLM-RoBERTa model achieved the highest performance with an F1 score of 0.7701, outperforming the specialized Arabic models. This work underscores the complexities of AI-generated text detection and highlights the strong generalization capabilities of multilingual models.

Ali Zain, Sareem Farooqui, Muhammad Rafi

This paper presents presents three distinct systems developed for the M-DAIGT shared task on detecting AI generated content in news articles and academic abstracts. The systems includes: (1) A fine-tuned RoBERTa-base classifier, (2) A classical TF-IDF + Support Vector Machine (SVM) classifier , and (3) An Innovative ensemble model named Candace, leveraging probabilistic features extracted from multiple Llama-3.2 models processed by a customTransformer encoder.The RoBERTa-based system emerged as the most performant, achieving near-perfect results on both development and test sets.

Awais Ahmed, Sufian Hameed, Muhammad Rafi et al.

Anomaly detection is a crucial step for preventing malicious activities in the network and keeping resources available all the time for legitimate users. It is noticed from various studies that classical anomaly detectors work well with small and sampled data, but the chances of failures increase with real-time (non-sampled data) traffic data. In this paper, we will be exploring security analytic techniques for DDoS anomaly detection using different machine learning techniques. In this paper, we are proposing a novel approach which deals with real traffic as input to the system. Further, we study and compare the performance factor of our proposed framework on three different testbeds including normal commodity hardware, low-end system, and high-end system. Hardware details of testbeds are discussed in the respective section. Further in this paper, we investigate the performance of the classifiers in (near) real-time detection of anomalies attacks. This study also focused on the feature selection process that is as important for the anomaly detection process as it is for general modeling problems. Several techniques have been studied for feature selection and it is observed that proper feature selection can increase performance in terms of model's execution time - which totally depends upon the traffic file or traffic capturing process.

Bilal Hayat Butt, Muhammad Rafi, Arsal Jamal et al.

Research is a continuous phenomenon. It is recursive in nature. Every research is based on some earlier research outcome. A general approach in reviewing the literature for a problem is to categorize earlier work for the same problem as positive and negative citations. In this paper, we propose a novel automated technique, which classifies whether an earlier work is cited as sentiment positive or sentiment negative. Our approach first extracted the portion of the cited text from citing paper. Using a sentiment lexicon we classify the citation as positive or negative by picking a window of at most five (5) sentences around the cited place (corpus). We have used Naïve-Bayes Classifier for sentiment analysis. The algorithm is evaluated on a manually annotated and class labelled collection of 150 research papers from the domain of computer science. Our preliminary results show an accuracy of 80%. We assert that our approach can be generalized to classification of scientific research papers in different disciplines.

Muhammad Rafi, Farnaz Amin, Mohammad Shahid Shaikh

Document clustering is an unsupervised approach in which a large collection of documents (corpus) is subdivided into smaller, meaningful, identifiable, and verifiable sub-groups (clusters). Meaningful representation of documents and implicitly identifying the patterns, on which this separation is performed, is the challenging part of document clustering. We have proposed a document clustering technique using graph based document representation with constraints. A graph data structure can easily capture the non-linear relationships of nodes, document contains various feature terms that can be non-linearly connected hence a graph can easily represents this information. Constrains, are explicit conditions for document clustering where background knowledge is use to set the direction for Linking or Not-Linking a set of documents for a target clusters, thus guiding the clustering process. We deemed clustering is an ill-define problem, there can be many clustering results. Background knowledge can be used to drive the clustering algorithm in the right direction. We have proposed three different types of constraints, Instance level, corpus level and cluster level constraints. A new algorithm Constrained HAC is also proposed which will incorporate Instance level constraints as prior knowledge; it will guide the clustering process leading to better results. Extensive set of experiments have been performed on both synthetic and standard document clustering datasets, results are compared on standard clustering measures like: purity, entropy and F-measure. Results clearly establish that our proposed approach leads to improvement in cluster quality.

Muhammad Rafi, Mohammad Shahid Shaikh

A major computational burden, while performing document clustering, is the calculation of similarity measure between a pair of documents. Similarity measure is a function that assigns a real number between 0 and 1 to a pair of documents, depending upon the degree of similarity between them. A value of zero means that the documents are completely dissimilar whereas a value of one indicates that the documents are practically identical. Traditionally, vector-based models have been used for computing the document similarity. The vector-based models represent several features present in documents. These approaches to similarity measures, in general, cannot account for the semantics of the document. Documents written in human languages contain contexts and the words used to describe these contexts are generally semantically related. Motivated by this fact, many researchers have proposed seman-tic-based similarity measures by utilizing text annotation through external thesauruses like WordNet (a lexical database). In this paper, we define a semantic similarity measure based on documents represented in topic maps. Topic maps are rapidly becoming an industrial standard for knowledge representation with a focus for later search and extraction. The documents are transformed into a topic map based coded knowledge and the similarity between a pair of documents is represented as a correlation between the common patterns (sub-trees). The experimental studies on the text mining datasets reveal that this new similarity measure is more effective as compared to commonly used similarity measures in text clustering.

Muhammad Rafi, Mohammad Shahid Shaikh

Document classification is a task of assigning a new unclassified document to one of the predefined set of classes. The content based document classification uses the content of the document with some weighting criteria to assign it to one of the predefined classes. It is a major task in library science, electronic document management systems and information sciences. This paper investigates document classification by using two different classification techniques (1) Support Vector Machine (SVM) and (2) Relevance Vector Machine (RVM). SVM is a supervised machine learning technique that can be used for classification task. In its basic form, SVM represents the instances of the data into space and tries to separate the distinct classes by a maximum possible wide gap (hyper plane) that separates the classes. On the other hand RVM uses probabilistic measure to define this separation space. RVM uses Bayesian inference to obtain succinct solution, thus RVM uses significantly fewer basis functions. Experimental studies on three standard text classification datasets reveal that although RVM takes more training time, its classification is much better as compared to SVM.

Muhammad Rafi, Sundus Hassan, Mohammad Shahid Shaikh

A major computational burden, while performing document clustering, is the calculation of similarity measure between a pair of documents. Similarity measure is a function that assign a real number between 0 and 1 to a pair of documents, depending upon the degree of similarity between them. A value of zero means that the documents are completely dissimilar whereas a value of one indicates that the documents are practically identical. Traditionally, vector-based models have been used for computing the document similarity. The vector-based models represent several features present in documents. These approaches to similarity measures, in general, cannot account for the semantics of the document. Documents written in human languages contain contexts and the words used to describe these contexts are generally semantically related. Motivated by this fact, many researchers have proposed semantic-based similarity measures by utilizing text annotation through external thesauruses like WordNet (a lexical database). In this paper, we define a semantic similarity measure based on documents represented in topic maps. Topic maps are rapidly becoming an industrial standard for knowledge representation with a focus for later search and extraction. The documents are transformed into a topic map based coded knowledge and the similarity between a pair of documents is represented as a correlation between the common patterns. The experimental studies on the text mining datasets reveal that this new similarity measure is more effective as compared to commonly used similarity measures in text clustering.

Sundus Hassan, Muhammad Rafi, Muhammad Shahid Shaikh

The activity of labeling of documents according to their content is known as text categorization. Many experiments have been carried out to enhance text categorization by adding background knowledge to the document using knowledge repositories like Word Net, Open Project Directory (OPD), Wikipedia and Wikitology. In our previous work, we have carried out intensive experiments by extracting knowledge from Wikitology and evaluating the experiment on Support Vector Machine with 10- fold cross-validations. The results clearly indicate Wikitology is far better than other knowledge bases. In this paper we are comparing Support Vector Machine (SVM) and Naïve Bayes (NB) classifiers under text enrichment through Wikitology. We validated results with 10-fold cross validation and shown that NB gives an improvement of +28.78%, on the other hand SVM gives an improvement of +6.36% when compared with baseline results. Naïve Bayes classifier is better choice when external enriching is used through any external knowledge base.

Mehwish Aziz, Muhammad Rafi

Blogs-Online digital diary like application on web 2.0 has opened new and easy way to voice opinion, thoughts, and like-dislike of every Internet user to the World. Blogosphere has no doubt the largest user-generated content repository full of knowledge. The potential of this knowledge is still to be explored. Knowledge discovery from this new genre is quite difficult and challenging as it is totally different from other popular genre of web-applications like World Wide Web (WWW). Blog-posts unlike web documents are small in size, thus lack in context and contain relaxed grammatical structures. Hence, standard text similarity measure fails to provide good results. In this paper, specialized requirements for comparing a pair of blog-posts is thoroughly investigated. Based on this we proposed a novel algorithm for sentence oriented semantic similarity measure of a pair of blog-posts. We applied this algorithm on a subset of political blogosphere of Pakistan, to cluster the blogs on different issues of political realm and to identify the influential bloggers.

Mehwish Aziz, Muhammad Rafi

Text mining is becoming vital as Web 2.0 offers collaborative content creation and sharing. Now Researchers have growing interest in text mining methods for discovering knowledge. Text mining researchers come from variety of areas like: Natural Language Processing, Computational Linguistic, Machine Learning, and Statistics. A typical text mining application involves preprocessing of text, stemming and lemmatization, tagging and annotation, deriving knowledge patterns, evaluating and interpreting the results. There are numerous approaches for performing text mining tasks, like: clustering, categorization, sentimental analysis, and summarization. There is a growing need to standardize the evaluation of these tasks. One major component of establishing standardization is to provide standard datasets for these tasks. Although there are various standard datasets available for traditional text mining tasks, but there are very few and expensive datasets for blog-mining task. Blogs, a new genre in web 2.0 is a digital diary of web user, which has chronological entries and contains a lot of useful knowledge, thus offers a lot of challenges and opportunities for text mining. In this paper, we report a new indigenous dataset for Pakistani Political Blogosphere. The paper describes the process of data collection, organization, and standardization. We have used this dataset for carrying out various text mining tasks for blogosphere, like: blog-search, political sentiments analysis and tracking, identification of influential blogger, and clustering of the blog-posts. We wish to offer this dataset free for others who aspire to pursue further in this domain.