5 papers
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Domenic Rosati, Alessa Carbo, Ali Dadsetan +5
Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recover…
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
Domenic Rosati, Ali Dadsetan, Hong Huang +5
A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech. Preventing su…
SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
Dorsa Soleymani, Ali Dadsetan, Frank Rudzicz
Differential privacy (DP) provides strong protection for sensitive data, but often reduces model performance and fairness, especially for underrepresented groups. One major reason…
Re-examining Low Rank adaptation for private LLM fine-tuning
Ali Dadsetan, Frank Rudzicz
Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and differentially private stochastic gradient descent (DP-SGD) -- which clips per-sam…
Can large language models be privacy preserving and fair medical coders?
Ali Dadsetan, Dorsa Soleymani, Xijie Zeng +1
Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy…