Introduces hybrid noise and novel coupling analysis to achieve the first convergent hidden-state DP bound for zeroth-order optimization.
arXiv preprint arXiv:2401.04343 (2024)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
DP-SGD-RC applies Hutchinson and Hutch++ estimators to approximate per-sample gradient norms for clipping in DP-SGD, claiming competitive privacy noise multipliers and utility on Llama 3.2-1B with reduced memory.
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.
citing papers explorer
-
Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
Introduces hybrid noise and novel coupling analysis to achieve the first convergent hidden-state DP bound for zeroth-order optimization.
-
Probing Memorization of Tabular In-Context Learning
A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.
-
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
-
Efficient DP-SGD for LLMs with Randomized Clipping
DP-SGD-RC applies Hutchinson and Hutch++ estimators to approximate per-sample gradient norms for clipping in DP-SGD, claiming competitive privacy noise multipliers and utility on Llama 3.2-1B with reduced memory.
-
Memory-Efficient Differentially Private Training with Gradient Random Projection
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.
- Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD