PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
cs.LG, cs.AI, cs.CR
Submitted: 2026-05-07
Updated: 2026-11-06
Code: https://github.com/bilgehanertan/paczero
Terminology
Sources
- SIMD-PAC-DB: Pretty Performant PAC Privacy
- Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
- Unlocking High-Accuracy Differentially Private Image Classification through Scale
- Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
- An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
- Towards Understanding the Impact of Model Size on Differential Private Classification
- Robustness Threats of Differential Privacy
- Opacus: User-Friendly Differential Privacy Library in PyTorch
- OPT: Open Pre-trained Transformer Language Models
- Private Prediction via PAC Privacy
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis