Claim · 2014-12-20 · publication · Stated in source · Supported

The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Explaining and Harnessing Adversarial Examples → states its contribution → The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature.

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Explaining and Harnessing Adversarial Examplesstates its contribution ↓The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature.

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2014-12-20 · publication Records dated 2014 →

Scope and limitsThe paper's own description of its contribution; not an assessment of it.

The evidence 01

primary sourceSupports the claim

Explaining and Harnessing Adversarial Examples

arXiv · 2014-12-20

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“We argue instead that the primary cause of neural networks’ vulnerability to adversarial perturbation is their linear nature.”

Location in source arXiv v1, PDF p. 1, abstract

Machine-checked · 2026-10-31

Source details and check notes

Authors: Ian J. Goodfellow; Jonathon Shlens; Christian Szegedy
Version: arXiv:1412.6572v1, submitted 20 December 2014 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 abef582a0fc65807d3509af5315e071b1356506b54ba31862bbd6f9d5bd657fd). The author list is the byline as printed on the first page.
Version date: 2014-12-20
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy, “Explaining and Harnessing Adversarial Examples”, 2014-12-20.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, key papers (research/key-papers). The quotation (18 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A paper or other publication describes its own contribution, quoted from the expression the record names, usually its abstract or introduction. The record is the document’s own description, not an assessment: a claim of priority or novelty it contains is the document’s claim, flagged as such, and says nothing about earlier or later work.

Date. Date of the arXiv version quoted, submitted 20 December 2014 (UTC); later versions may word it differently.

Record ID kp-states-explaining-harnessing-adversarial-examples-2014-1