Invalid validation in `QuantizeAndDequantizeV2`

Impact The validation in tf.rawops.QuantizeAndDequantizeV2 allows invalid values for axis argument: python import tensorflow as tf inputtensor = tf.constant0.0, shape=1, dtype=float inputmin = tf.constant-10.0 inputmax = tf.constant-10.0 tf.rawops.QuantizeAndDequantizeV2 input=inputtensor,...

Incomplete validation in `SparseAdd`

Impact Incomplete validation in SparseAdd results in allowing attackers to exploit undefined behavior dereferencing null pointers as well as write outside of bounds of heap allocated data: python import tensorflow as tf aindices = tf.zeros10, 97, dtype=tf.int64 avalues = tf.zeros10, dtype=tf.int6...

Heap OOB and null pointer dereference in `RaggedTensorToTensor`

Impact Due to lack of validation in tf.rawops.RaggedTensorToTensor, an attacker can exploit an undefined behavior if input arguments are empty: python import tensorflow as tf shape = tf.constant-1, -1, shape=2, dtype=tf.int64 values = tf.constant, shape=0, dtype=tf.int64 defaultvalue =...

Heap OOB read in TFLite

Impact A specially crafted TFLite model could trigger an OOB read on heap in the TFLite implementation of SplitV: cc const int inputsize = SizeOfDimensioninput, axisvalue; If axisvalue is not a value between 0 and NumDimensionsinput, then the SizeOfDimension function will access data outside the...

Integer overflow in TFLite memory allocation

Impact The TFLite code for allocating TFLiteIntArrays is vulnerable to an integer overflow issue: cc int TfLiteIntArrayGetSizeInBytesint size static TfLiteIntArray dummy; return sizeofdummy + sizeofdummy.data0 size; An attacker can craft a model such that the size multiplier is so large that the...

Division by zero in TFLite's implementation of hashtable lookup

Impact The TFLite implementation of hashtable lookup is vulnerable to a division by zero error: cc const int numrows = SizeOfDimensionvalue, 0; const int rowbytes = value-bytes / numrows; An attacker can craft a model such that values's first dimension would be 0. Patches We have patched the issu...

Heap OOB write in TFLite

Impact A specially crafted TFLite model could trigger an OOB write on heap in the TFLite implementation of ArgMin/ArgMax: cc TfLiteIntArray outputdims = TfLiteIntArrayCreateNumDimensionsinput - 1; int j = 0; for int i = 0; i dataj = SizeOfDimensioninput, i; ++j; If axisvalue is not a value betwee...

Division by zero in TFLite's implementation of `DepthwiseConv`

Impact The implementation of the DepthwiseConv TFLite operator is vulnerable to a division by zero error: cc int numinputchannels = SizeOfDimensioninput, 3; TFLITEENSUREEQcontext, numfilterchannels % numinputchannels, 0; An attacker can craft a model such that input's fourth dimension would be 0...

Integer overflow in TFLite concatentation

Impact The TFLite implementation of concatenation is vulnerable to an integer overflow issue: cc for int d = 0; d dims-size; ++d if d == axis sumaxis += t-dims-dataaxis; else TFLITEENSUREEQcontext, t-dims-datad, t0-dims-datad; An attacker can craft a model such that the dimensions of one of the...

Division by zero in TFLite's implementation of `OneHot`

Impact The implementation of the OneHot TFLite operator is vulnerable to a division by zero error: cc int prefixdimsize = 1; for int i = 0; i dims-datai; const int suffixdimsize = NumElementsopcontext.indices / prefixdimsize; An attacker can craft a model such that at least one of the dimensions ...

Division by zero in TFLite's implementation of Split

Impact The implementation of the Split TFLite operator is vulnerable to a division by zero error: cc TFLITEENSUREMSGcontext, inputsize % numsplits == 0, "Not an even split"; const int slicesize = inputsize / numsplits; An attacker can craft a model such that numsplits would be 0. Patches We have...

Division by zero in TFLite's implementation of `SVDF`

Impact The implementation of the SVDF TFLite operator is vulnerable to a division by zero error: cc const int rank = params-rank; ... TFLITEENSUREEQcontext, numfilters % rank, 0; An attacker can craft a model such that params-rank would be 0. Patches We have patched the issue in GitHub commit...

Division by zero in TFLite's implementation of `EmbeddingLookup`

The implementation of the EmbeddingLookup TFLite operator is vulnerable to a division by zero error: cc const int rowsize = SizeOfDimensionvalue, 0; const int rowbytes = value-bytes / rowsize; An attacker can craft a model such that the first dimension of the value input is 0. Patches We have...

Division by zero in TFLite's implementation of `DepthToSpace`

Impact The implementation of the DepthToSpace TFLite operator is vulnerable to a division by zero error: cc const int blocksize = params-blocksize; ... const int inputchannels = input-dims-data3; ... int outputchannels = inputchannels / blocksize / blocksize; An attacker can craft a model such th...

Division by zero in TFLite's convolution code

Impact TFLite's convolution code has multiple division where the divisor is controlled by the user and not checked to be non-zero. For example: cc const int inputsize = NumElementsinput / SizeOfDimensioninput, 0; Patches We have patched the issue in GitHub commit...

Division by zero in TFLite's implementation of `BatchToSpaceNd`

Impact The implementation of the BatchToSpaceNd TFLite operator is vulnerable to a division by zero error: cc TFLITEENSUREEQcontext, outputbatchsize % blockshapedim, 0; outputbatchsize = outputbatchsize / blockshapedim; An attacker can craft a model such that one dimension of the block input is 0...

Null pointer dereference in TFLite's `Reshape` operator

Impact The fix for CVE-2020-15209 missed the case when the target shape of Reshape operator is given by the elements of a 1-D tensor. As such, the fix for the vulnerability allowed passing a null-buffer-backed tensor with a 1D shape: cc if tensor-data.raw == nullptr && tensor-bytes 0 if...

Stack overflow due to looping TFLite subgraph

Impact TFlite graphs must not have loops between nodes. However, this condition was not checked and an attacker could craft models that would result in infinite loop during evaluation. In certain cases, the infinite loop would be replaced by stack overflow due to too many recursive calls. For...

Heap OOB read in TFLite's implementation of `Minimum` or `Maximum`

Impact The implementations of the Minimum and Maximum TFLite operators can be used to read data outside of bounds of heap allocated objects, if any of the two input tensor arguments are empty. This is because the broadcasting implementation indexes in both tensors with the same index but does not...

Division by zero in TFLite's implementation of `GatherNd`

Impact The reference implementation of the GatherNd TFLite operator is vulnerable to a division by zero error: cc ret.dimstocounti = remainflatsize / paramsshape.Dimsi; An attacker can craft a model such that params input would be an empty tensor. In turn, paramsshape.Dims. would be zero, in at...