SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09751 · 2024

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2403.09751.json · badge: /api/ran/2403.09751.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
royweiss1/GPT_Keylogger canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
make_input Ran
ran; our contract draft was wrong, not the code
royweiss1/GPT_Keylogger/archive/fine_tune_T5_first.py
code served (permissive licence) · get_code("06b70c44d7d79671")
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, through the batch API) and returned str. 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

torch.manual_seed(0)

# Analyze the function: make_input takes special_tokens parameter
# and returns a formatted string with those tokens
# special_tokens appears to be a string or string-like object that gets interpolated into the f-string

special_tokens = "[CLS] [SEP] [PAD] [UNK]"

ARGS = {
    "special_tokens": special_tokens
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
make_input Ran
ran; our contract draft was wrong, not the code
royweiss1/GPT_Keylogger/archive/fine_tune_T5_with_context.py
code served (permissive licence) · get_code("7572fe54650b47e4")
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, through the batch API) and returned str. 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

torch.manual_seed(0)

# Construct arguments for make_input function
context = "The ancient library contained scrolls from many civilizations."
special_tokens = ["[ANCIENT]", "[LIBRARY]", "[SCROLLS]"]

ARGS = {
    "context": context,
    "special_tokens": special_tokens
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
apply_token Not yet run
unverified (harvested, no recorded run)
royweiss1/GPT_Keylogger/archive/fine_tune_T5_first.py
code served (permissive licence) · get_code("7440f0a84d98629e")
How it ran

no invocation recorded.

encoding_lengths Not yet run
unverified (harvested, no recorded run)
royweiss1/GPT_Keylogger/archive/fine_tune_T5_first.py
code served (permissive licence) · get_code("e4e573d7601e989a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

AI assistants are becoming an integral part of society, used for asking advice or help in personal and confidential issues. In this paper, we unveil a novel side-channel that can be used to read encrypted responses from AI Assistants over the web: the token-length side-channel. We found that many vendors, including OpenAI and Microsoft, have this side-channel. However, inferring the content of a response from a token-length sequence alone proves challenging. This is because tokens are akin to words, and responses can be several sentences long leading to millions of grammatically correct sentences. In this paper, we show how this can be overcome by (1) utilizing the power of a large language model (LLM) to translate these sequences, (2) providing the LLM with inter-sentence context to narrow the search space and (3) performing a known-plaintext attack by fine-tuning the model on the target model's writing style. Using these methods, we were able to accurately reconstruct 29\% of an AI assistant's responses and successfully infer the topic from 55\% of them. To demonstrate the threat, we performed the attack on OpenAI's ChatGPT-4 and Microsoft's Copilot on both browser and API traffic.

For agents

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

get_harvested_code_for_paper("2403.09751")
get_code_for_paper("2403.09751")
have("2403.09751")

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

curl https://syntology.ai/api/ran/2403.09751.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09751.svg)](https://syntology.ai/paper/2403.09751)

Connect an agent — have() is free.