ADVAITHA VETAGIRI
SRM University, Andhra Pradesh, Gudlavalleru Engineering College, National Institute Of Technology Silchar, Bapatla Engineering College
Research areas: Computer Science · Artificial Intelligence · Hate Speech and Cyberbullying Detection · Sentiment Analysis and Opinion Mining · Topic Modeling
0000-0002-0651-4171
About
Professionally, I'm a PhD holder from NIT Silchar specializing in Generative AI, Multimodality, Adversarial Attacks, Natural Language Processing, and Cybersecurity, with a mission to build safer AI systems. I've shared my findings in over 12 research papers across global stages like EMNLP and CLEF, but my favorite part of the journey is always the people I meet and the students I get to inspire.
My current research focuses on Generative AI, Multimodal Learning, Adversarial Machine Learning, Cybersecurity, and Natural Language Processing, particularly in multimodal hate speech detection and low-resource language processing.
In the long term, I aspire to advance the field of trustworthy and human-aligned AI by building resilient multimodal systems, designing universal adversarial defense frameworks, and creating inclusive AI technologies that preserve and empower underrepresented languages and cultures.
Employment
-
SRM University, Andhra Pradesh Assistant Professor2025 - Present
-
Gudlavalleru Engineering College ASSISTANT PROFESSOR2020 - 2021
Education
- 2021 - 2026
-
Bapatla Engineering College B.Tech2013 - 2017
Projects & Funding
Projects & funding information is unavailable.
Publications (20)
- Cross-modal feature manipulation for multimodal adversarial perturbation generation on AI-generated MULTImodaL hATE Save
- A deep dive into automated sexism detection using fine-tuned deep learning and large language models Save
- Mitigating Adversarial Attacks in Ai-Generated Multimodal Hate Save
- MULTILATE: A Synthetic Dataset on AI-Generated MULTImodaL hATE Speech Save
- A Deep Dive into Automated Sexism Detection Using Fine-Tuned Deep Learning and Large Language Models Save
- Breaking the Silence Detecting and Mitigating Gendered Abuse in Hindi, Tamil, and Indian English Online Spaces Save
- Cracking Down on Digital Misogyny with MULTILATE a MULTImodaL hATE Detection System Save
- Findings of WMT 2024 Shared Task on Low-Resource Indic Languages Translation Save
- Multilate Classifier: A Novel Emsemble of Cnn-Bilstm with Resnet-Based Multimodal Classifier for Ai-Generated Hate Speech Detection Save
- Real-Time Helmet Detection and Number Plate Extraction Using Computer Vision Save
- “Breaking the Silence” Detecting and Mitigating Gendered Abuse in Hindi, Tamil, and Indian English Online Spaces Save
- “Multilate”: A Synthetic Dataset for Multimodal Hate Speech Detection Save
- CNLP-NITS at SemEval-2023 Task 10: Online sexism prediction, PREDHATE! Save
- Addressing Hate Speech: ATLANTIS for Efficient Hate Span Detection Save
- Addressing Hate Speech: ATLANTIS for Efficient Hate Span Detection Save
- Examining Hate Speech Detection Across Multiple Indo-Aryan Languages in Tasks 1 & 4 Save
- Examining Hate Speech Detection Across Multiple Indo-Aryan Languages in Tasks 1 & 4 Save
- Leveraging GPT-2 for Automated Classification of Online Sexist Content Save
- An accurate foreground moving object detection based on segmentation techniques and optimal classifier Save
- ETHICAL HACKING TOOLS & TECHNIQUES TO PRESERVE SECURITY Save