activity
20242026
collaborators

9 papers

cs.CL2026

PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction

Pirzada Suhail, Nagasai Saketh Naidu, Atanu R Sinha +1

Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating…

cs.LG2025

TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection

Pirzada Suhail, Rehna Afroz, Amit Sethi

Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable mach…

cs.LG2025

EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation Matching

Pirzada Suhail, Aditya Anand, Amit Sethi

Machine learning models, by virtue of training, learn a large repertoire of decision rules for any given input, and any one of these may suffice to justify a prediction. However, i…

cs.LG2025

Network Inversion for Uncertainty-Aware Out-of-Distribution Detection

Pirzada Suhail, Rehna Afroz, Gouranga Bala +1

Out-of-distribution (OOD) detection and uncertainty estimation (UE) are critical components for building safe machine learning systems, especially in real-world scenarios where une…

cs.CV2025

Activation Matching for Explanation Generation

Pirzada Suhail, Aditya Anand, Amit Sethi

In this paper we introduce an activation-matching--based approach to generate minimal, faithful explanations for the decision-making of a pretrained classifier on any given image.…

cs.LG2025

Network Inversion for Generating Confidently Classified Counterfeits

Pirzada Suhail, Pravesh Khaparde, Amit Sethi

In vision classification, generating inputs that elicit confident predictions is key to understanding model behavior and reliability, especially under adversarial or out-of-distrib…