Unelicitable Backdoors via Cryptographic Transformer Circuits

Andis Draguns, Andrew Gritsevskiy, S. Motwani, Christian Schröder de Witt
2/3/2026
Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{draguns2026unelicitable,
  title  = {Unelicitable Backdoors via Cryptographic Transformer Circuits},
  author = {Andis Draguns and Andrew Gritsevskiy and S. Motwani and Christian Schröder de Witt},
  year   = {2026},
  url    = {https://www.semanticscholar.org/paper/df7b350d758bcbbba9b42b51cc164db0cbd27609},
  journal = {NEURIPS 2024 2024}
}

Discussion