DP-ES: Differentially Private Evolution Strategies for Prompt Optimization

arXiv:2610.06236 · cs.CR, cs.CL · Submitted 2026-10-05 · Read on arXiv

cs.CR, cs.CL

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: Accepted at EMNLP 2026 (Main Conference). Code: https://github.com/StephCpa/dp-es

Code: https://github.com/StephCpa/dp-es

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Differentially Private — 1× in this paper · explained in 3 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
• Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
• Differentially Private In-Context Learning with Nearest Neighbor Search
• Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
• DeepSeek-V3 Technical Report
• Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
• DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
• Qwen2.5 Technical Report
• TextGrad: Automatic "Differentiation" via Text

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs