SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.03057 · 2023

Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2309.03057.json · badge: /api/ran/2309.03057.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
alohachen/hide-and-seek canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_merged_spans Ran
ran, violated the contract we drafted
alohachen/hide-and-seek/utils.py
code served (permissive licence) · get_code("74e8d38927ad6778")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family int, shape (5, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import re

def merge_spans(intervals):
    """合并有交集的区间"""
    intervals.sort(key=lambda x: x[0])
    merged = []
    for interval in intervals:
        if not merged or merged[-1][1] < interval[0]:
            merged.append(interval)
        else:
            merged[-1][1] = max(merged[-1][1], interval[1])
    return merged

def get_merged_spans(text, ents):
    """获取实体的位置区间,同时合并有交集的部分"""
    all_spans = []
    for ent in ents:
        try:
            spans = [[match.start(), match.end()] for match in re.finditer(ent, text)]
            all_spans.extend(spans)
        except:
            pass
    merged_spans = np.array(merge_spans(all_spans))
    return merged_spans

# Setup code
text = "The quick brown fox jumps over the lazy dog. The fox is quick."
ents = ["fox", "quick", "the"]

ARGS = {
    "text": text,
    "ents": ents
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (5, 2) — shape (5, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_labeled_spans Ran
ran; our contract draft was wrong, not the code
alohachen/hide-and-seek/utils.py
code served (permissive licence) · get_code("8c16a2a23e72af71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned set. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Construct arguments for merge_labeled_spans
spacy_list = [
    (0, 5, "PERSON"),
    (5, 10, "PERSON"),
    (10, 15, "ORG"),
    (20, 25, "PERSON"),
]

text = "Alice works at Google and Bob is here"

return_positions = False

ARGS = {
    "spacy_list": spacy_list,
    "text": text,
    "return_positions": return_positions,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_spans Ran
ran; our contract draft was wrong, not the code
alohachen/hide-and-seek/utils.py
code served (permissive licence) · get_code("3607ba6f6d41e8ba")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# The function merge_spans takes a list of intervals (tuples/lists with start and end points)
# and merges overlapping ones. It sorts by start point and merges intervals with overlap.

# Create a list of intervals (each interval is a tuple of [start, end])
intervals = [
    [1, 3],
    [2, 6],
    [8, 10],
    [15, 18]
]

ARGS = {
    "intervals": intervals
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning using multi-party computation (MPC) has proven to be impractical for LLM applications due to its time-consuming and communication-intensive nature. While lightweight anonymization techniques can protect private information in prompts through substitution or masking, they fail to recover sensitive data replaced in the LLM-generated results. In this paper, we expand the application scenarios of anonymization techniques by training a small local model to de-anonymize the LLM's returned results with minimal computational overhead. We introduce the HaS framework, where "H(ide)" and "S(eek)" represent its two core processes: hiding private entities for anonymization and seeking private entities for de-anonymization, respectively. To quantitatively assess HaS's privacy protection performance, we propose both black-box and white-box adversarial models. Furthermore, we conduct experiments to evaluate HaS's usability in translation and classification tasks. The experimental findings demonstrate that the HaS framework achieves an optimal balance between privacy protection and utility.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.03057")
get_code_for_paper("2309.03057")
have("2309.03057")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.03057.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.03057.svg)](https://syntology.ai/paper/2309.03057)

Connect an agent — have() is free.