Explaining and Harnessing Adversarial Examples
Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Christian Szegedy
- Dates
- Published 2014-12-20 authorship evidence
- Exact source
- Explaining and Harnessing Adversarial Examples International Conference on Learning Representations · published 2015 · ICLR 2015 (conference poster programme). ICLR 2015 published no proceedings volume; the programme lists the paper. Located by the cross-family machine check on 2026-10-30 (item A035; Conference poster programme, title entry), at the precision of its source; not read again at admission.
- Explaining and Harnessing Adversarial Examples arXiv · published 2014-12-20 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 1b7f4280a1f50b26a9d2679dc879d5c6d5578237438439a2788560240c5d35de). Submission history as arXiv records it (UTC): v1 20 December 2014; v2 25 February 2015; v3 20 March 2015. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
- Explaining and Harnessing Adversarial Examples arXiv · published 2014-12-20 · 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.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cited by · 3
Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.
- Alignment for Advanced Machine Learning SystemsAlignment for Advanced Machine Learning Systems cites Explaining and Harnessing Adversarial Examples.2016 · publication · Stated in source · Supported Inspect claim & evidence ↗Alignment for Advanced Machine Learning Systems: document page →
- Concrete Problems in AI SafetyConcrete Problems in AI Safety cites Explaining and Harnessing Adversarial Examples.2016-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Concrete Problems in AI Safety: document page →
- Scalable agent alignment via reward modeling: a research directionScalable agent alignment via reward modeling: a research direction cites Explaining and Harnessing Adversarial Examples.2018-11-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Scalable agent alignment via reward modeling: a research direction: document page →
Not recorded for this document: cites · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document says it adds
The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.
- In its own wordsThe authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature.“We argue instead that the primary cause of neural networks’ vulnerability to adversarial perturbation is their linear nature.” arXiv v1, PDF p. 1, abstract2014-12-20 · publication · Stated in source · Supported Inspect claim & evidence ↗
- In its own wordsThe paper states that this view yields a simple and fast method for generating adversarial examples.“Moreover, this view yields a simple and fast method of generating adversarial examples.” arXiv v1, PDF p. 1, abstract2014-12-20 · publication · Stated in source · Supported Inspect claim & evidence ↗