5 papers
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints
Yash Sinha, Murari Mandal, Mohan Kankanhalli
User data spread across multiple modalities has popularized multi-modal recommender systems (MMRS). They recommend diverse content such as products, social media posts, TikTok reel…
OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs
Debdeep Sanyal, Umakanta Maharana, Yash Sinha +4
Role-based access control (RBAC) and hierarchical structures are foundational to how information flows and decisions are made within virtually all organizations. As the potential o…
Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
Yash Sinha, Manit Baser, Murari Mandal +2
Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation.…
Nine Ways to Break Copyright Law and Why Our LLM Won't: A Fair Use Aligned Generation Framework
Aakash Sen Sharma, Debdeep Sanyal, Priyansh Srivastava +4
Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant et…
UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
Yash Sinha, Murari Mandal, Mohan Kankanhalli
The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentiall…