SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.09470 · 2019

Characterizing Attacks on Deep Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 2 have no contract verdict; 4 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/1907.09470.json · badge: /api/ran/1907.09470.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
ssg-research/flare community (classifier label)
classifier basis: plan_row
7 ran · 0 no recorded run
FunctionStatusWhere it lives
activation_bound Ran
ran; our contract draft was wrong, not the code
ssg-research/flare/src/ibp.py
code served (permissive licence) · get_code("69017b3a991e0815")
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 tuple. 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple neural network layer that can be called on tensors
layer = nn.Linear(4, 3)

# Create prev_upper and prev_lower tensors
# These should be compatible with the layer's input dimension (4)
prev_upper = torch.randn(2, 4)
prev_lower = torch.randn(2, 4)

ARGS = {
    "layer": layer,
    "prev_upper": prev_upper,
    "prev_lower": prev_lower
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
init Ran
ran; our contract draft was wrong, not the code
ssg-research/flare/src/agents/models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ArnaudFickinger/adversarial-surprise, is pointer only (licence: NONE) · get_code("9de355e93051e4ad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ArnaudFickinger/adversarial-surprise, and GitHub detected no licence in that repository 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.

initial_bounds Ran
ran, violated the contract we drafted
ssg-research/flare/src/ibp.py
code served (permissive licence) · get_code("cfb1c3dd218b92f0")
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 tuple, ndim 5, dtype family float; 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

torch.manual_seed(0)

# x0 is a tensor of shape (b, c, h, w)
# The function performs simple arithmetic operations on it
x0 = torch.randn(2, 3, 4, 5)

# epsilon is a scalar value for the perturbation bounds
epsilon = 0.1

ARGS = {
    "x0": x0,
    "epsilon": epsilon,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 5, dtype family float — a tuple 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
post_process Ran
ran on a synthesized input
ssg-research/flare/src/agents/action_conditional_video_prediction.py
code served (permissive licence) · get_code("3ba7c8da77c3ab15")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# y is used in multiplication (y * 255.0), so it should be a tensor
y = torch.randn(2, 4)

# mean_obs is used in addition (... + mean_obs), so it should be a tensor
mean_obs = torch.randn(2, 4)

ARGS = {
    "y": y,
    "mean_obs": mean_obs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
pre_process Ran
ran on a synthesized input
ssg-research/flare/src/agents/action_conditional_video_prediction.py
code served (permissive licence) · get_code("a39e3b63ff5b97d2")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# x: tensor to be normalized
x = torch.randn(2, 4)

# mean_obs: mean observation value to subtract
mean_obs = torch.randn(2, 4)

ARGS = {
    "x": x,
    "mean_obs": mean_obs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
project_lp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ssg-research/flare/src/attack_utils/attacks.py
code served (permissive licence) · get_code("24b246433997a7b8")
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 ndarray, ndim 1, dtype family float, shape (4,) 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

# Define arguments for project_lp function
v = np.array([0.5, -0.3, 0.8, -0.2])  # Small vector to project
xi = 0.1  # Radius/bound for projection
p = np.inf  # Use np.inf norm

ARGS = {
    'v': v,
    'xi': xi,
    'p': p
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family float, shape (4,) — shape (4,) 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
weighted_bound Ran
ran; our contract draft was wrong, not the code
ssg-research/flare/src/ibp.py
code served (permissive licence) · get_code("eba320329ae9cb63")
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 tuple. 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small linear layer for testing
linear_layer = nn.Linear(4, 3)

# Create small tensors for prev_upper and prev_lower
# Shape: (batch=2, features=4) for linear, or (batch=2, channels=4, height=5, width=5) for conv2d
prev_upper_linear = torch.randn(2, 4)
prev_lower_linear = torch.randn(2, 4)

# Create a small Conv2d layer for testing
conv_layer = nn.Conv2d(in_channels=4, out_channels=3, kernel_size=3, stride=1, padding=1)

# Create small tensors for conv2d
prev_upper_conv = torch.randn(2, 4, 5, 5)
prev_lower_conv = torch.randn(2, 4, 5, 5)

# Test with linear layer
ARGS = {
    "layer": linear_layer,
    "prev_upper": prev_upper_linear,
    "prev_lower": prev_lower_linear,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 later) and 0 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
init 34 other papers
5 dated earlier, 29 later · 5 only as an assembly brick
1705.05363 (2017-05)
Curiosity-driven Exploration by Self-supervised Prediction
1706.02275 (2017-06)
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
1810.12894 (2018-10)
Exploration by Random Network Distillation
and 31 more not named here
activation_bound 5 other papers
5 later
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2111.06063 (2021-11)
On the Equivalence between Neural Network and Support Vector Machine
2402.02165 (2024-02)
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
and 2 more not named here
initial_bounds 4 other papers
4 later
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2111.06063 (2021-11)
On the Equivalence between Neural Network and Support Vector Machine
2402.02165 (2024-02)
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
and 1 more not named here
weighted_bound 4 other papers
4 later
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
2402.02165 (2024-02)
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
2403.04050 (2024-03)
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
and 1 more not named here
post_process 1 other paper
1 later
2106.08746 (2021-06)
Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses
pre_process 1 other paper
1 later
2106.08746 (2021-06)
Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses
project_lp 1 other paper
1 dated earlier
1610.08401 (2016-10)
Universal adversarial perturbations

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

Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations. However, some attacks assume full availability of the victim model, and some require a huge amount of computation, making them less feasible for real world applications. In this work, we make further explorations of the vulnerabilities of DRL by studying other aspects of attacks on DRL using realistic and efficient attacks. First, we adapt and propose efficient black-box attacks when we do not have access to DRL model parameters. Second, to address the high computational demands of existing attacks, we introduce efficient online sequential attacks that exploit temporal consistency across consecutive steps. Third, we explore the possibility of an attacker perturbing other aspects in the DRL setting, such as the environment dynamics. Finally, to account for imperfections in how an attacker would inject perturbations in the physical world, we devise a method for generating a robust physical perturbations to be printed. The attack is evaluated on a real-world robot under various conditions. We conduct extensive experiments both in simulation such as Atari games, robotics and autonomous driving, and on real-world robotics, to compare the effectiveness of the proposed attacks with baseline approaches. To the best of our knowledge, we are the first to apply adversarial attacks on DRL systems to physical robots.

For agents

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

get_harvested_code_for_paper("1907.09470")
get_code_for_paper("1907.09470")
have("1907.09470")

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

curl https://syntology.ai/api/ran/1907.09470.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.09470.svg)](https://syntology.ai/paper/1907.09470)

Connect an agent — have() is free.