Fix OOB buffer index in GetFlatbufferTensorBuffer - #3648
Open
cloudymonstera wants to merge 1 commit into
Open
Conversation
Reject tensor.buffer() values that are out of range for the model buffers vector before indexing, matching the existing check used by the compression-metadata path in the same file. Without this guard, a crafted .tflite can cause an out-of-bounds read via flatbuffers::Vector::operator[] during AllocateTensors().
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
tensor.buffer()before indexing the modelbuffersvector inGetFlatbufferTensorBuffer.buffer_index >= buffers->size()).flatbuffers::Vector::operator[]duringMicroInterpreter::AllocateTensors()when loading a crafted.tflite.Test plan
buffers.size()==2andtensor.buffer()==65535no longer reaches an OOB index (returns null buffer / fails allocation cleanly instead of reading past the vector)tensor.buffer()indices still allocate and invoke successfullyMade with Cursor