SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09947 · NeurIPS · 2022

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Nicholas Carlini, Maura Pintor, Fabio Roli, Battista Biggio, Luca Demetrio, Angelo Sotgiu, Ambra Demontis

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 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/2106.09947.json · badge: /api/ran/2106.09947.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
pralab/IndicatorsOfAttackFailure canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
as_tensor Ran
ran, honoured the contract we drafted
pralab/IndicatorsOfAttackFailure/src/indicators/indicators.py
pointer only (licence: GPL-3.0) · get_code("889b2308f6689ed6")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, pralab/IndicatorsOfAttackFailure, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken under more rigorous evaluations. Although guidelines and best practices have been suggested to improve current adversarial robustness evaluations, the lack of automatic testing and debugging tools makes it difficult to apply these recommendations in a systematic manner. In this work, we overcome these limitations by: (i) categorizing attack failures based on how they affect the optimization of gradientbased attacks, while also unveiling two novel failures affecting many popular attack implementations and past evaluations; (ii) proposing six novel indicators of failure, to automatically detect the presence of such failures in the attack optimization process; and (iii) suggesting a systematic protocol to apply the corresponding fixes. Our extensive experimental analysis, involving more than 15 models in 3 distinct application domains, shows that our indicators of failure can be used to debug and improve current adversarial robustness evaluations, thereby providing a first concrete step towards automatizing and systematizing them. Our open-source code is available at: https://github.com/pralab/IndicatorsOfAttackFailure.

For agents

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

get_harvested_code_for_paper("2106.09947")
get_code_for_paper("2106.09947")
have("2106.09947")

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

curl https://syntology.ai/api/ran/2106.09947.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09947.svg)](https://syntology.ai/paper/2106.09947)

Connect an agent — have() is free.