CVE-2026-73557

A flaw was found in vLLM, an inference and serving engine for large language models. An incomplete remediation for a previous vulnerability CVE-2025-62164 can be bypassed. This occurs when concurrent prompt parts are processed, leading to a race condition in the handling of sparse tensors. This...

EUVD-2026-51267

SGLang contains an unauthenticated RCE in /loadloraadapterfromtensors via bypass of SafeUnpickler’s incomplete denylist, allowing arbitrary command execution through crafted base64-encoded pickle payloads...

Out-of-bounds Read

Overview onnx is an Open Neural Network Exchange Affected versions of this package are vulnerable to Out-of-bounds Read in the adaptgemm76 function when processing input tensors with fewer than two dimensions. An attacker can cause a crash or potentially leak adjacent heap memory by providing a...

PYSEC-2026-3222 Invalid char to bool conversion when printing a tensor

Impact When printing a tensor, we get it's data as a const char array since that's the underlying storage and then we typecast it to the element type. However, conversions from char to bool are undefined if the char is not 0 or 1, so sanitizers/fuzzers will crash. Patches We have patched the issu...

PYSEC-2026-3297 Overflow in `tf.keras.losses.poisson`

Impact tf.keras.losses.poisson receives a ypred and ytrue that are passed through functor::mul in BinaryOp. If the resulting dimensions overflow an int32, TensorFlow will crash due to a size mismatch during broadcast assignment. python import numpy as np import tensorflow as tf truevalue =...

PYSEC-2026-3384 Segfault via invalid attributes in `pywrap_tfe_src.cc`

Impact If a list of quantized tensors is assigned to an attribute, the pywrap code fails to parse the tensor and returns a nullptr, which is not caught. An example can be seen in tf.compat.v1.extractvolumepatches by passing in quantized tensors as input ksizes. python import numpy as np import...

PYSEC-2026-3262 Segfault via invalid attributes in `pywrap_tfe_src.cc`

Impact If a list of quantized tensors is assigned to an attribute, the pywrap code fails to parse the tensor and returns a nullptr, which is not caught. An example can be seen in tf.compat.v1.extractvolumepatches by passing in quantized tensors as input ksizes. python import numpy as np import...

PYSEC-2026-3126 Overflow in `FusedResizeAndPadConv2D`

Impact When tf.rawops.FusedResizeAndPadConv2D is given a large tensor shape, it overflows. python import tensorflow as tf mode = "REFLECT" strides = 1, 1, 1, 1 padding = "SAME" resizealigncorners = False input = tf.constant147, shape=3,3,1,1, dtype=tf.float16 size =...

PYSEC-2026-3290 Overflow in `FusedResizeAndPadConv2D`

Impact When tf.rawops.FusedResizeAndPadConv2D is given a large tensor shape, it overflows. python import tensorflow as tf mode = "REFLECT" strides = 1, 1, 1, 1 padding = "SAME" resizealigncorners = False input = tf.constant147, shape=3,3,1,1, dtype=tf.float16 size =...

PYSEC-2026-3379 TensorFlow vulnerable to segfault in `Requantize`

Impact If Requantize is given inputmin, inputmax, requestedoutputmin, requestedoutputmax tensors of a nonzero rank, it results in a segfault that can be used to trigger a denial of service attack. python import tensorflow as tf outtype = tf.quint8 input = tf.constant1, shape=3, dtype=tf.qint32...

PYSEC-2026-3152 TensorFlow vulnerable to `CHECK` fail in `FakeQuantWithMinMaxVarsPerChannel`

Impact If FakeQuantWithMinMaxVarsPerChannel is given min or max tensors of a rank other than one, it results in a CHECK fail that can be used to trigger a denial of service attack. python import tensorflow as tf numbits = 8 narrowrange = False inputs = tf.constant0, shape=4, dtype=tf.float32 min ...

PYSEC-2026-1954 Invalid char to bool conversion when printing a tensor

Impact When printing a tensor, we get it's data as a const char array since that's the underlying storage and then we typecast it to the element type. However, conversions from char to bool are undefined if the char is not 0 or 1, so sanitizers/fuzzers will crash. Patches We have patched the issu...

PYSEC-2026-964 Overflow in `FusedResizeAndPadConv2D`

Impact When tf.rawops.FusedResizeAndPadConv2D is given a large tensor shape, it overflows. python import tensorflow as tf mode = "REFLECT" strides = 1, 1, 1, 1 padding = "SAME" resizealigncorners = False input = tf.constant147, shape=3,3,1,1, dtype=tf.float16 size =...

PYSEC-2026-1050 Segfault via invalid attributes in `pywrap_tfe_src.cc`

Impact If a list of quantized tensors is assigned to an attribute, the pywrap code fails to parse the tensor and returns a nullptr, which is not caught. An example can be seen in tf.compat.v1.extractvolumepatches by passing in quantized tensors as input ksizes. python import numpy as np import...

PYSEC-2026-977 TensorFlow vulnerable to `CHECK` fail in `FakeQuantWithMinMaxVars`

Impact If FakeQuantWithMinMaxVars is given min or max tensors of a nonzero rank, it results in a CHECK fail that can be used to trigger a denial of service attack. python import tensorflow as tf numbits = 8 narrowrange = False inputs = tf.constant0, shape=2,3, dtype=tf.float32 min = tf.constant0,...

CVE-2026-53923

vLLM is an inference and serving engine for large language models LLMs. From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels csrc/quantization/gguf/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...

CVE-2026-56340

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-41664

Integer overflow in memory copy size calculation in Samsung Open Source ONE could lead to invalid memory operations with large tensor shapes. Affected version is prior to commit 1.30.0...

CVE-2026-41665

Integer overflow in scratch buffer initialization size calculation in Samsung Open Source ONE cause incorrect memory initialization for large intermediate tensors. Affected version is prior to commit 1.30.0...

CVE-2026-40449

Integer overflow in buffer size calculation could result in out of bounds memory access when handling large tensors in Samsung Open Source ONE. Affected version is prior to commit 1.30.0...