2 papers
cs.CV2026
Source Models Leak What They Shouldn't : Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas +1
The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and lea…
cs.LG2025
Exact Unlearning of Finetuning Data via Model Merging at Scale
Kevin Kuo, Amrith Setlur, Kartik Srinivas +2
Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. Ho…