Newest papers

Poisoning-Based Backdoors Are Not Cryptographic

Masahiro Kaneko · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28045 · open-access PDF

Russian

Чтобы защититься от атак с заднеприводом на нейронные сети, защитник должен определить функцию верификатора, которая определяет, является ли вход триггером, а не отвергать отдельные триггеры в изоляции, поскольку нападающий может генерировать новые триггеры, удовлетворяющие тому же верификатору быстрее, чем их можно заблокировать.

Machine translation (Meta M2M100); the English original follows.

Abstract

To defend against backdoor attacks on neural networks, the defender must identify the verifier function that determines whether an input is a trigger, rather than rejecting individual triggers in isolation, since an attacker can generate new triggers satisfying the same verifier faster than they can be blocked. If a backdoor verifier could be installed with the asymmetry of a cryptographic authentication scheme, in which only the attacker can produce trigger inputs while the defender cannot reverse-engineer the verifier from observations, learning-based defense would be impossible in principle

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28045, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange