activity
20242026
collaborators

6 papers

cs.CR2026

Anchors that Don't Lift: Understanding Supply Chain Driven Kernel Lock-In and Governance-Mediated Mitigation Strategies in SOHO Devices

Ritwik Badola, Rajdeep Ghosh, Ashita Gupta +2

Small Office/Home Office (SOHO) devices are widely popular, yet often attacked due to security vulnerabilities in their firmware, affecting thousands of devices. These security vul…

cs.CL2026

Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization

Gunjan Balde, Soumyadeep Roy, Mainack Mondal +1

Large language models pretrained on general-domain corpora often exhibit tokenization inefficiencies when applied to specialized domains. Although continual pretraining for domain…

cs.CV2026

Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes

Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde +4

Advances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on adding imperceptible…

cs.CR2025

"I wasn't sure if this is indeed a security risk": Data-driven Understanding of Security Issue Reporting in GitHub Repositories of Open Source npm Packages

Rajdeep Ghosh, Shiladitya De, Mainack Mondal

The npm (Node Package Manager) ecosystem is the most important package manager for JavaScript development with millions of users. Consequently, a plethora of earlier work investiga…

cs.CL2025

Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings

Gunjan Balde, Soumyadeep Roy, Mainack Mondal +1

Large Language Models (LLMs) recently achieved great success in medical text summarization by simply using in-context learning. However, these recent efforts do not perform fine-gr…

cs.CL2024

Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models

Gunjan Balde, Soumyadeep Roy, Mainack Mondal +1

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models…