Mahnoor Shahid

Mahnoor Shahid

Detection and mitigation of critical web vulnerabilities and attacks like cross-site scripting (XSS), and cross-site request forgery (CSRF) have been a great concern in the field of web security. Such web attacks are evolving and becoming more challenging to detect. Several ideas from different perspectives have been put forth that can be used to improve the performance of detecting these web vulnerabilities and preventing the attacks from happening. Machine learning techniques have lately been used by researchers to defend against XSS and CSRF, and given the positive findings, it can be concluded that it is a promising research direction. The objective of this paper is to briefly report on the research works that have been published in this direction of applying classical and advanced machine learning to identify and prevent XSS and CSRF. The purpose of providing this survey is to address different machine learning approaches that have been implemented, understand the key takeaway of every research, discuss their positive impact and the downsides that persists, so that it can help the researchers to determine the best direction to develop new approaches for their own research and to encourage researchers to focus towards the intersection between web security and machine learning.

Mahnoor Shahid, Mark Koch, Niklas Schneider

Two distinct tasks - generating photorealistic pictures from given text prompts and transferring the style of a painting to a real image to make it appear as though it were done by an artist, have been addressed many times, and several approaches have been proposed to accomplish them. However, the intersection of these two, i.e., generating paintings from a given caption, is a relatively unexplored area with little data available. In this paper, we have explored two distinct strategies and have integrated them together. First strategy is to generate photorealistic images and then apply style transfer and the second strategy is to train an image generation model on real images with captions and then fine-tune it on captioned paintings later. These two models are evaluated using different metrics as well as a user study is conducted to get human feedback on the produced results.

Mahnoor Shahid, Hannes Rothe

Compositional generalization remains a foundational weakness of modern neural networks, limiting their robustness and applicability in domains requiring out-of-distribution reasoning. A central, yet unverified, assumption in neuro-symbolic AI is that compositional reasoning will emerge as a byproduct of successful symbol grounding. This work presents the first systematic empirical analysis to challenge this assumption by disentangling the contributions of grounding and reasoning. To operationalize this investigation, we introduce the Iterative Logic Tensor Network ($i$LTN), a fully differentiable architecture designed for multi-step deduction. Using a formal taxonomy of generalization -- probing for novel entities, unseen relations, and complex rule compositions -- we demonstrate that a model trained solely on a grounding objective fails to generalize. In contrast, our full $i$LTN, trained jointly on perceptual grounding and multi-step reasoning, achieves high zero-shot accuracy across all tasks. Our findings provide conclusive evidence that symbol grounding, while necessary, is insufficient for generalization, establishing that reasoning is not an emergent property but a distinct capability that requires an explicit learning objective.

Mahnoor Shahid, Hannes Rothe

Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments. This work introduces AGEL-Comp, a neuro-symbolic AI agent architecture designed to address this challenge by grounding actions of the agent. AGEL-Comp integrates three core innovations: (1) a dynamic Causal Program Graph (CPG) as a world model, representing procedural and causal knowledge as a directed hypergraph; (2) an Inductive Logic Programming (ILP) engine that synthesizes new Horn clauses from experiential feedback, grounding symbolic knowledge through interaction; and (3) a hybrid reasoning core where an LLM proposes a set of candidate sub-goals that are verified for logical consistency by a Neural Theorem Prover (NTP). Together, these components operationalize a deduction--abduction learning cycle: enabling the agent to deduce plans and abductively expand its symbolic world model, while a neural adaptation phase keeps its reasoning engine aligned with new knowledge. We propose an evaluation protocol within the \texttt{Retro Quest} simulation environment to probe for compositional generalization scenarios to evaluate our AGEL agent. Our findings clearly indicate the better performance of our AGEL model over pure LLM-based models. Our framework presents a principled path toward agents that build an explicit, interpretable, and compositionally structured understanding of their world.

Shahrukh Khan, Mahnoor Shahid, Navdeeppal Singh

In this work, we evaluate the adversarial robustness of BERT models trained on German Hate Speech datasets. We also complement our evaluation with two novel white-box character and word level attacks thereby contributing to the range of attacks available. Furthermore, we also perform a comparison of two novel character-level defense strategies and evaluate their robustness with one another.

Shahrukh Khan, Mahnoor Shahid

Sentiment Analysis typically refers to using natural language processing, text analysis and computational linguistics to extract affect and emotion based information from text data. Our work explores how we can effectively use deep neural networks in transfer learning and joint dual input learning settings to effectively classify sentiments and detect hate speech in Hindi and Bengali data. We start by training Word2Vec word embeddings for Hindi \textbf{HASOC dataset} and Bengali hate speech and then train LSTM and subsequently, employ parameter sharing based transfer learning to Bengali sentiment classifiers by reusing and fine-tuning the trained weights of Hindi classifiers with both classifier being used as baseline in our study. Finally, we use BiLSTM with self attention in joint dual input learning setting where we train a single neural network on Hindi and Bengali dataset simultaneously using their respective embeddings.