[Security] Add tensor depth limit in JSON parsing#4137
Open
micrictor wants to merge 1 commit into
Open
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
micrictor
force-pushed
the
fix-json-tensor-depth-limit
branch
from
018318e to
1b5ab92
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
In the fix for CVE-2025-0649 in #4133, a max limit was placed on JSON stringification to avoid DoS from arbitrary inputs to ModelServer.
This change adds a similar limit to the recursion depth of nested tensors in JSON parsing, which occurs earlier in the lifetime of a request to a model's
predictAPI. Without this change, a caller can crash the server with a crafted call topredict.The hard-coded limit of
1024was chosen somewhat arbitrarily - the MobileNetV2 model only has a tensor depth of 4, so there's a very large safety factor. At a depth of 1024, the entire call stack is still likely to be under 1MB in memory.