Mechanism · Training-transcript verification (proof-of-learning)

Structurally correct spoofs exploit tolerance thresholds and sampled checks

On this page

← All known flaws

CriticalDemonstrated attackOpen

Fang et al., including the original proposers, present spoofing strategies that work across PoL configurations at "a fraction of the cost of previous spoofing strategies" 4. The strategies exploit the tolerance that verification must allow for hardware noise, and the choice of which updates the verifier re-runs 4.

Sources: [4]

Search

Full search page