LATENT REFERENCES / TAG2
adversarial examples
Original title: adversarial examples
This reference note belongs to Tag2 in Latent References, an archive curated by Keigo Yoshida. Its archive region is Alan Turing. The note preserves its source text and links so that readers can trace the material behind the 3D map.
- Collection
- Tag2
- Archive region
- Alan Turing
Archived reference note
English translation of the archived note. JP shows the original text. Source links and literal code are retained; the translation does not update or independently verify the source claims.
Reports that such images could be created by merely adding tiny amounts of noise (Adversarial Perturbation) prompted numerous subsequent studies.
https://scrapbox.io/files/6633a96586930c0024d4ed75.png
#machinelearning
このような画像の作成が微小なノイズ（Adversarial Perturbation; 敵対的摂動）を足すだけで実現できることが報告され、そこから数々の研究が発表されています。
https://scrapbox.io/files/6633a96586930c0024d4ed75.png
#machinelearning
Source updated 2024-08-07 · Snapshot 2026-10-08
Source links and calculated neighbors
Cosine values measure shared lexical features, not truth, agreement or identical meaning. Original reference links are labeled separately.
- CAN Creative Adversarial NetworksComputed lexical cosine similarity 0.317 · shared title, text, tags and references
- Turing MachineComputed lexical cosine similarity 0.229 · shared title, text, tags and references
- Ian GoodfellowComputed lexical cosine similarity 0.221 · shared title, text, tags and references
- RhythmCANComputed lexical cosine similarity 0.215 · shared title, text, tags and references
- Harold CohenComputed lexical cosine similarity 0.212 · shared title, text, tags and references
- Deep DreamComputed lexical cosine similarity 0.206 · shared title, text, tags and references
- Interactive Evolutionary ComputationComputed lexical cosine similarity 0.204 · shared title, text, tags and references
- edmond de belamyComputed lexical cosine similarity 0.186 · shared title, text, tags and references