14 papers
PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents
Pirzada Suhail, Menglin Xia, Xuchao Zhang +3
Memory systems are becoming a core component of LLM agents, but constructing and maintaining memory remains expensive because it relies on repeated calls to large proprietary langu…
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…
Med-CAM: Minimal Evidence for Explaining Medical Decision Making
Pirzada Suhail, Aditya Anand, Amit Sethi
Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medic…
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…
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.…
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…
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…
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…
Privacy Preserving Properties of Vision Classifiers
Pirzada Suhail, Amit Sethi
Vision classifiers are often trained on proprietary datasets containing sensitive information, yet the models themselves are frequently shared openly under the privacy-preserving a…
Shortcut Learning Susceptibility in Vision Classifiers
Pirzada Suhail, Vrinda Goel, Amit Sethi
Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust an…
Network Inversion and Its Applications
Pirzada Suhail, Hao Tang, Amit Sethi
Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes.…
Network Inversion for Training-Like Data Reconstruction
Pirzada Suhail, Amit Sethi
Machine Learning models are often trained on proprietary and private data that cannot be shared, though the trained models themselves are distributed openly assuming that sharing m…
Network Inversion of Convolutional Neural Nets
Pirzada Suhail, Amit Sethi
Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes.…
Network Inversion of Binarised Neural Nets
Pirzada Suhail, Supratik Chakraborty, Amit Sethi
While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical cha…