Concentration:
- range query authentication
- data stream
- partially materialized digest (PMD)
- one-shot and sliding window queries
Problem Definition
Use the sliding window model ( query the latest n tuple) to search the data stream.
Definition : we see a data stream S as a non-limited length series S=(a1,a2...). Each tiime only one tuple arrives. We only condier a size n sliding window containing (a_{t-n+1}, a_{t-n+2}, ... a_{t-1}, a_t). This is the sliding window data stream model.
PMD strategy authentication
The disadvantage of traditional MHT:
- redundant verification. The internal hash number is rather high.
- rely too much on the single root signature: once the single signature is corrupted or forged, no matter the result is correct or not, the client cannot verify the authenticity of the data.
- fail to fast locate the corrupted position: the client can only know the result is corrupted but fail to find the specific wrong tuple. The DO needs to resend all the tuple and the server needs to reconstruct the tree.
