Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

SurrogateShield: Beyond Redaction for High-Utility, Privacy-Preserving LLM Interactions

Sherwin Vishesh Jathanna · Jun 28, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries contain personally identifiable information (PII), the data persists on remote infrastructure subject to breach, subpoena, or policy change. Placeholder redaction (the prevailing mitigation) suppresses PII at the cost of semantic coherence, producing structurally degraded queries and correspondingly degraded responses. We present SurrogateShield, a client-side proxy that substitutes detected PII with locally generated, type-consistent surrogate values prior to transmission and restores originals in the response. No real PII crosses the network boundary. Detection runs through a three-stage cascade (PatternScan, EntityTrace, and ContextGuard) covering 22 PII types and quasi-identifier combinations grounded in Sweeney's k-anonymity framework. Surrogate-to-original mappings are sealed in an AES-256-GCM encrypted per-conversation ShadowMap that never leaves the device. Evaluations on a 1,124-query corpus demonstrate that the cascade reliably detects PII, achieving an overall F1 score of 98.87%. Surrogate substitution substantially outperforms placeholder redaction in semantic utility, yielding a 13.26 pp improvement in BERTScore (roberta-large), from 81.59% to 94.85%. Within this corpus, the local pipeline restricted real PII transmission across all tested query types; in a 100-query adversarial trial, a prompted LLM adversary recovered no original values from surrogate-substituted messages.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This paper looks adjacent to evaluation work, but not like a strong protocol reference.
  • The available metadata is too thin to trust this as a primary source.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 35%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control."

Reported Metrics

partial

F1, Bertscore, Coherence

Useful for evaluation criteria comparison.

"Placeholder redaction (the prevailing mitigation) suppresses PII at the cost of semantic coherence, producing structurally degraded queries and correspondingly degraded responses."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

f1bertscorecoherence

Research Brief

Metadata summary

LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control.
  • When those queries contain personally identifiable information (PII), the data persists on remote infrastructure subject to breach, subpoena, or policy change.
  • Placeholder redaction (the prevailing mitigation) suppresses PII at the cost of semantic coherence, producing structurally degraded queries and correspondingly degraded responses.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics, Tool-use evaluation) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

F1

Research Summary

Contribution Summary

  • We present SurrogateShield, a client-side proxy that substitutes detected PII with locally generated, type-consistent surrogate values prior to transmission and restores originals in the response.
  • Evaluations on a 1,124-query corpus demonstrate that the cascade reliably detects PII, achieving an overall F1 score of 98.87%.
  • Surrogate substitution substantially outperforms placeholder redaction in semantic utility, yielding a 13.26 pp improvement in BERTScore (roberta-large), from 81.59% to 94.85%.

Why It Matters For Eval

  • Evaluations on a 1,124-query corpus demonstrate that the cascade reliably detects PII, achieving an overall F1 score of 98.87%.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: f1, bertscore, coherence

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.