3 papers
cs.CR2026
CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
Akshit Jindal, Saket Anand, Chetan Arora +1
Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language mode…
cs.LG2025
Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
Atharv Goel, Sharat Agarwal, Saket Anand +1
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution s…
cs.LG2023
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection
Akshit Jindal, Vikram Goyal, Saket Anand +1
Machine Learning (ML) models become vulnerable to Model Stealing Attacks (MSA) when they are deployed as a service. In such attacks, the deployed model is queried repeatedly to bui…