SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07152 · 2023

No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML

arXiv · PDF · Open in the Atlas

Code that ran

8 of 15 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 7 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/2310.07152.json · badge: /api/ran/2310.07152.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
ziqi-zhang/teeslice-artifact canonical (classifier label)
classifier basis: census
8 ran · 7 no recorded run
FunctionStatusWhere it lives
Lx_distance Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/utils_shadownet.py
pointer only (licence: NONE) · get_code("1fc66939068066e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

fchecker_variance Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/utils_shadownet.py
pointer only (licence: NONE) · get_code("0ba85727fd94c3d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_net Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/knockoff_train.py
pointer only (licence: NONE) · get_code("64e9bca534ec9a24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_databatch Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/demoloader/downsampled_imagenet.py
pointer only (licence: NONE) · get_code("2c39ccfcd5989720")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_target_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ziqi-zhang/teeslice-artifact/membership-inference/train_layer.py
pointer only (licence: NONE) · get_code("d8513d247401ec1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

shadownet_layer Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/utils_shadownet.py
pointer only (licence: NONE) · get_code("a41f3ea5d5aab0b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_step Ran
ran, honoured the contract we drafted
ziqi-zhang/teeslice-artifact/membership-inference/knockoff_train.py
pointer only (licence: NONE) · get_code("104afcbc0f6f4143")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unpickle Ran
ran; our contract draft was wrong, not the code
ziqi-zhang/teeslice-artifact/membership-inference/demoloader/downsampled_imagenet.py
pointer only (licence: NONE); the stored copy get_code serves, from haiyunyao/diversemix, is pointer only (licence: NONE) · get_code("4ebc0e09cb353eac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

alexnet Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/models/alexnet.py
pointer only (licence: NONE) · get_code("18aa3a782441967c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_confidence_gap Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/mem_attack.py
pointer only (licence: NONE) · get_code("9abbfa903ffc4510")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_generalization_gap Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/mem_attack.py
pointer only (licence: NONE) · get_code("dd0b2bf99e413935")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/models/alexnet.py
pointer only (licence: NONE) · get_code("405ae35edc541ea3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_value Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/gol.py
pointer only (licence: NONE) · get_code("840eea9045ad3fe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

samples_to_transferset Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/train_layer.py
pointer only (licence: NONE) · get_code("5352dbef4078e55a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

soft_cross_entropy Not yet run
unverified (harvested, no recorded run)
ziqi-zhang/teeslice-artifact/membership-inference/knockoff_train.py
pointer only (licence: NONE) · get_code("20c1f5f89a49698b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziqi-zhang/teeslice-artifact when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 14 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.

FunctionAlso present inEarliest-datedOthers named
unpickle 7 other papers
4 dated earlier, 3 later
1911.07205 (2019-11)
REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data
2104.08984 (2021-04)
Contrastive Learning Improves Model Robustness Under Label Noise
2202.03299 (2022-02)
Training OOD Detectors in their Natural Habitats
and 4 more not named here

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

On-device ML introduces new security challenges: DNN models become white-box accessible to device users. Based on white-box information, adversaries can conduct effective model stealing (MS) and membership inference attack (MIA). Using Trusted Execution Environments (TEEs) to shield on-device DNN models aims to downgrade (easy) white-box attacks to (harder) black-box attacks. However, one major shortcoming is the sharply increased latency (up to 50X). To accelerate TEE-shield DNN computation with GPUs, researchers proposed several model partition techniques. These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE. This paper benchmarks existing TSDP solutions using both MS and MIA across a variety of DNN models, datasets, and metrics. We show important findings that existing TSDP solutions are vulnerable to privacy-stealing attacks and are not as safe as commonly believed. We also unveil the inherent difficulty in deciding optimal DNN partition configurations (i.e., the highest security with minimal utility cost) for present TSDP solutions. The experiments show that such ``sweet spot'' configurations vary across datasets and models. Based on lessons harvested from the experiments, we present TEESlice, a novel TSDP method that defends against MS and MIA during DNN inference. TEESlice follows a partition-before-training strategy, which allows for accurate separation between privacy-related weights from public weights. TEESlice delivers the same security protection as shielding the entire DNN model inside TEE (the ``upper-bound'' security guarantees) with over 10X less overhead (in both experimental and real-world environments) than prior TSDP solutions and no accuracy loss.

For agents

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

get_harvested_code_for_paper("2310.07152")
get_code_for_paper("2310.07152")
have("2310.07152")

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

curl https://syntology.ai/api/ran/2310.07152.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.07152.svg)](https://syntology.ai/paper/2310.07152)

Connect an agent — have() is free.