Copybara import of the project: - #11082
Merged
Merged
Conversation
… subscripts AveragePool2D, MaxPool2D, Conv2D, DepthwiseConv2D, and TransposeConv2D all access fixed shape indices (shape[0]..shape[3]) on input, filter, and output tensors without first checking that the shape vector is large enough. A crafted TFLite model with a wrong-rank tensor triggers a null pointer dereference during XNNPACK subgraph compilation at model load time. Add rank size checks before the first shape subscript access in each function, following the pattern already present in TransposeConvOperation::ToXnnpack() (lines 1649-1653).
copybara-service
Bot
force-pushed
the
test_971399026
branch
from
September 1, 2026 18:57
5a6b8a7 to
a02f9fd
Compare
…ssing-rank-checks PiperOrigin-RevId: 974682030
copybara-service
Bot
force-pushed
the
test_971399026
branch
from
September 1, 2026 20:44
a02f9fd to
8c02ee3
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Copybara import of the project:
--
4013867 by destro4evr-rgb destro4evr@proton.me:
litert/xnnpack: add rank guards to Conv/Pool ToXnnpack() before shape subscripts
AveragePool2D, MaxPool2D, Conv2D, DepthwiseConv2D, and TransposeConv2D
all access fixed shape indices (shape[0]..shape[3]) on input, filter, and
output tensors without first checking that the shape vector is large enough.
A crafted TFLite model with a wrong-rank tensor triggers a null pointer
dereference during XNNPACK subgraph compilation at model load time.
Add rank size checks before the first shape subscript access in each
function, following the pattern already present in
TransposeConvOperation::ToXnnpack() (lines 1649-1653).
FUTURE_COPYBARA_INTEGRATE_REVIEW=#11057 from destro4evr-rgb:fix/litert-conv-pool-missing-rank-checks 4013867