AI Sec Watch

TensorFlow (an open source machine learning platform) versions before 2.12.0 and 2.11.1 have a Floating Point Exception bug in TensorListSplit with XLA (a compiler that speeds up machine learning computations). This bug could cause the program to crash when certain operations are performed.

TensorFlow, an open source platform for machine learning, has a bug in the `tf.raw_ops.LookupTableImportV2` function where it cannot properly handle scalar values (single values, not arrays) in the `values` parameter, causing an NPE (null pointer exception, when the program tries to use a value that doesn't exist). This is a type of vulnerability called NULL Pointer Dereference (CWE-476).

TensorFlow (an open source platform for machine learning) has a vulnerability called out-of-bounds access (a bug where code tries to read or write data outside the memory area it should access), caused by mismatched integer type sizes (using different number formats where the same one was expected). The issue can be fixed by updating to TensorFlow version 2.12.0 or 2.11.1.

TensorFlow (an open source machine learning platform) versions before 2.12.0 and 2.11.1 have a null pointer dereference (a crash caused by trying to access memory that doesn't exist) in a specific feature called QuantizedMatMulWithBiasAndDequantize when MKL (a math optimization library) is enabled. This bug can cause the software to crash or behave unexpectedly.

TensorFlow (an open source platform for machine learning) has a bug in the `tf.raw_ops.AvgPoolGrad` function where invalid input values can cause a floating point exception (a crash due to an illegal math operation). This affects TensorFlow versions before 2.12.0 and 2.11.1.

TensorFlow (an open-source machine learning platform) versions before 2.12.0 and 2.11.1 have a vulnerability that allows attackers to access heap memory (the part of a computer's memory used for dynamic storage) that shouldn't be accessible, potentially causing the program to crash or allowing remote code execution (running commands on a system remotely without authorization). This is caused by heap-based buffer overflow and out-of-bounds read errors (reading data from memory locations outside the intended boundaries).

TensorFlow, an open source machine learning platform, had an integer overflow vulnerability (a bug where calculations exceed the maximum number a computer can store) in versions before 2.12.0 and 2.11.1. The bug occurred when processing video frames with certain dimensions, potentially affecting full HD screencasts with at least 346 frames.

TensorFlow, an open source machine learning platform, had a floating point exception (a math error that crashes a program) in its AudioSpectrogram component before versions 2.12.0 and 2.11.1. This bug could cause the software to crash when processing certain audio data.

TensorFlow (an open source platform for machine learning) versions before 2.12.0 and 2.11.1 have a bug where the SparseSparseMaximum function crashes with a null pointer error (when the program tries to access memory that doesn't exist) if given invalid sparse tensors (multi-dimensional arrays with mostly empty values) as inputs. This is a stability issue that can cause the program to fail.