AxiomLimit · AI inference · for a technical reader
Where deletion receipts can be fooled: the lab’s exact wording
The lab’s own sentences and figures for this result, word for word, in its working terms, with its limits in plain words where the lab’s text cannot be reprinted. The plain account is on the result’s page; it says the same things in plain words.
The lab’s plain-English sentence
…the lab wrote two checkers for a "deletion receipt" (a signed note saying the data was destroyed) and, on a small setup built over an ordinary shared file rather than an AI serving system, showed six concrete ways such a receipt can check out while the data is still recoverable or was never deleted
- including one where both of its checkers accept a receipt from a colluding auditor when nothing was erased
In the lab’s words
the campaign publishes six demonstrated limits
The limit to read first, in the lab’s words
SIM-ONLY over an mmap file
Part of the lab’s record (claim and limits) is not reprinted here because it names internal files this site does not publish or uses internal working terms.
More
- The plain account of this result: the problem, what was shown, what it means for a buyer, who we expect would buy, why now, why you can trust the check, and what it does not show yet.
- This result’s file, the source of every sentence above.