Papers by Najrin Sultana

3 papers
From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: LLMs can provide substantial zero-shot performance on diverse tasks, but it is crucial to assess their robustness against adversarial inputs.
Approach: They introduce Static Deceptor and Dynamic Deceptr to generate adversarial examples . they produce subtle and natural-looking adversarials that preserve semantic similarity to text .
Outcome: The proposed attacks are based on two LLM-based attacks that generate natural-looking examples that deceive the target LLM.
LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software (2026.acl-long)

Copied to clipboard

Challenge: Existing automated program-repair techniques focus on repairing memory corruptions, but they struggle with logical vulnerabilities because of their limited semantic understanding of the code and its expected behavior.
Approach: They evaluated a dataset of 122 logical vulnerabilities and a framework to evaluate patches for logical weaknesses.
Outcome: The proposed framework evaluates both traditional and LLM-based approaches for addressing real-world logical vulnerabilities.
BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset (2022.aacl-short)

Copied to clipboard

Challenge: Bangla is considered a low resource language in terms of language processing.
Approach: They propose a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline.
Outcome: The proposed pipeline ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations