AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

CVE-2020-15212: In TensorFlow Lite before versions 2.2.1 and 2.3.1, models using segment sum can trigger writes outside of bounds of hea

highvulnerability

security

Source: NVD/CVE DatabaseSeptember 25, 2020CVE-2020-15212

Summary

TensorFlow Lite versions before 2.2.1 and 2.3.1 have a vulnerability where negative values in the segment_ids tensor (an array of numbers used to group data) can cause the software to write data outside its allocated memory area, potentially crashing the program or corrupting memory. This vulnerability can be exploited by anyone who can modify the segment_ids data.

Solution / Mitigation

The issue is patched in TensorFlow versions 2.2.1 or 2.3.1. As a workaround for unpatched versions, users can add a custom Verifier (a validation tool) to the model loading code to check that all segment IDs are positive if they are stored in the model file, or add similar validation at runtime if they are generated during execution. However, if segment IDs are generated as outputs during inference, no workaround is available and upgrading to patched code is required.