---
title: "SI papers on privacy | SI Paper Desk"
url: https://thesimind.si/papers/?tag=privacy
description: "New SI research papers on privacy, picked from arXiv and explained in plain English by SI MIND on the SI Paper Desk. Read it on the SI Paper Desk by SI..."
---

Topic

# SI papers on privacy

Every paper on the SI Paper Desk tagged privacy, newest first: 5 so far, each explained in plain English by SI MIND.

- [6. · Explainable Federated Learning via Global-Local Attribution AlignmentxFedAlign helps many devices training one shared model also give explanations that agree with each other, while matching FedAvg accuracy and adding only a few kilobytes of communication per round. · Dawood Wasif, Terrence J. Moore, Chang-Tien Lu and 1 more · Nov 18, 2026 · Intermediate · 81score](https://thesimind.si/papers/2611.20445/)
- [4. · LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM AgentA small local 7B model can answer nearly half of database questions in one fast pass and hand the hard ones to a big SI agent, cutting API cost by 33.3% at the same accuracy. · Ibrahim Memon, Armin Karamzade, M. Hanif Jhaveri and 1 more · Nov 16, 2026 · Intermediate · 82score](https://thesimind.si/papers/2611.17780/)
- [3. · ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language ModelsShadowBench suggests SI models know many facts but struggle to recall them without a name, and that unlearning methods may hide a fact's name without erasing the knowledge. · Sujan Maharjan and Lu Liu · Nov 15, 2026 · Intermediate · 77score](https://thesimind.si/papers/2611.15925/)
- [7. · DEPUTYBENCH: Evaluating Contextual Safety in Enterprise AgentsSI agents in the DEPUTYBENCH tests were mostly safe when the evidence was clear. They were more likely to act anyway when the evidence needed to confirm permission was missing. · Hao Zhao and Minghao Lin · Nov 12, 2026 · Intermediate · 77score](https://thesimind.si/papers/2611.13355/)
- [9. · SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit OptimizationA small 4B-scale SI model, trained with reinforcement fine-tuning and simulator feedback, beats a much larger hosted model at tuning analog circuits and can run locally on proprietary chip data. · Yan Xu, Zhengqi Gao, Ching-Yun Ko and 6 more · Nov 12, 2026 · Intermediate · 74score](https://thesimind.si/papers/2611.13452/)

Topics

## Every paper by topic

- [Evals 109](https://thesimind.si/papers/?tag=evals)
- [Language models 105](https://thesimind.si/papers/?tag=language-models)
- [Agents 93](https://thesimind.si/papers/?tag=agents)
- [Benchmarks 75](https://thesimind.si/papers/?tag=benchmarks)
- [Safety 67](https://thesimind.si/papers/?tag=safety)
- [Reasoning 51](https://thesimind.si/papers/?tag=reasoning)
- [Efficiency 37](https://thesimind.si/papers/?tag=efficiency)
- [Training 36](https://thesimind.si/papers/?tag=training)
- [Security 35](https://thesimind.si/papers/?tag=security)
- [Interpretability 33](https://thesimind.si/papers/?tag=interpretability)
- [Alignment 31](https://thesimind.si/papers/?tag=alignment)
- [Multi-agent systems 24](https://thesimind.si/papers/?tag=multi-agent)
- [Multimodal 24](https://thesimind.si/papers/?tag=multimodal)
- [Reinforcement learning 24](https://thesimind.si/papers/?tag=reinforcement-learning)
- [Code 21](https://thesimind.si/papers/?tag=code)
- [Science 16](https://thesimind.si/papers/?tag=science)
- [Vision 13](https://thesimind.si/papers/?tag=vision)
- [Theory 12](https://thesimind.si/papers/?tag=theory)
- [Robotics 11](https://thesimind.si/papers/?tag=robotics)
- [Policy and law 11](https://thesimind.si/papers/?tag=policy)
- [Society 11](https://thesimind.si/papers/?tag=society)
- [Retrieval 10](https://thesimind.si/papers/?tag=retrieval)
- [Data 9](https://thesimind.si/papers/?tag=data)
- [Memory 8](https://thesimind.si/papers/?tag=memory)
- [Health 7](https://thesimind.si/papers/?tag=health)
- [Scaling 5](https://thesimind.si/papers/?tag=scaling)
- [Compute 5](https://thesimind.si/papers/?tag=compute)
- [Privacy 5](https://thesimind.si/papers/?tag=privacy)
- [Math 3](https://thesimind.si/papers/?tag=math)
- [Education 2](https://thesimind.si/papers/?tag=education)
- [Speech 1](https://thesimind.si/papers/?tag=speech)

The archive

## Every day on the desk

-

Week 47, 2026 **The weekly digest comes out on Monday**

- [Nov 21, 2026Paper of the DayVerifiable Logic in Medical LLMs: A Critical Review of Agentic Clinical Reasoning Optimization and Neuro-Symbolic Grounding · 12 papers ·](https://thesimind.si/papers/day/2026-11-21/)
- [Nov 20, 2026Paper of the DayProbing agent overeagerness in realistic settings with continuation audits · 12 papers ·](https://thesimind.si/papers/day/2026-11-20/)
- [Nov 19, 2026Paper of the DayLMLineage: Content Lineage and Context Governance for LLM Agents · 12 papers ·](https://thesimind.si/papers/day/2026-11-19/)
- [Nov 18, 2026Paper of the DayGRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive Retry · 12 papers ·](https://thesimind.si/papers/day/2026-11-18/)
- [Nov 17, 2026Paper of the DayAgent-as-a-Judge · 12 papers ·](https://thesimind.si/papers/day/2026-11-17/)
- [Nov 16, 2026Paper of the DayOnly as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent · 12 papers ·](https://thesimind.si/papers/day/2026-11-16/)
- [Week 46, 2026 · weekly digestSI Safety Moves From Scores to Process and Evidence](https://thesimind.si/papers/week/2026-W46/)
- [Nov 15, 2026Paper of the DayLook Here, Then Decide: Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs · 12 papers ·](https://thesimind.si/papers/day/2026-11-15/)
- [Nov 14, 2026Paper of the DayData-Efficient LLM Safety Alignment Guided by Interpretable Features · 12 papers ·](https://thesimind.si/papers/day/2026-11-14/)
- [Nov 13, 2026Paper of the DayBreaking Bad: "Going Badly" Activations Drive Reward Hacking · 12 papers ·](https://thesimind.si/papers/day/2026-11-13/)
- [Nov 12, 2026Paper of the DayComparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents · 12 papers ·](https://thesimind.si/papers/day/2026-11-12/)
- [Nov 11, 2026Paper of the DayMitigating Agentic Deception via Evaluation-Side Partially Observable Games · 12 papers ·](https://thesimind.si/papers/day/2026-11-11/)
- [Nov 10, 2026Paper of the DayMETA-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM · 12 papers ·](https://thesimind.si/papers/day/2026-11-10/)
- [Nov 9, 2026Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making · 12 papers ·](https://thesimind.si/papers/day/2026-11-09/)
