165 matches found
PYSEC-2026-3199 TensorFlow vulnerable to `CHECK` fail in `FakeQuantWithMinMaxVarsPerChannelGradient`
Impact When tf.quantization.fakequantwithminmaxvarsperchannelgradient receives input min or max of rank other than 1, it gives a CHECK fail that can trigger a denial of service attack. python import tensorflow as tf arg0=tf.random.uniformshape=1,1, dtype=tf.float32, maxval=None...
PYSEC-2026-3234 TensorFlow vulnerable to `CHECK` fail in `FakeQuantWithMinMaxVarsGradient`
Impact When tf.quantization.fakequantwithminmaxvarsgradient receives input min or max that is nonscalar, it gives a CHECK fail that can trigger a denial of service attack. python import tensorflow as tf import numpy as np arg0=tf.constantvalue=np.random.randomsize=2, 2, shape=2, 2, dtype=tf.float...
PYSEC-2026-3306 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-2026-3291 TensorFlow segfault TFLite converter on per-channel quantized transposed convolutions
Impact When converting transposed convolutions using per-channel weight quantization the converter segfaults and crashes the Python process. python import tensorflow as tf class QuantConv2DTransposedtf.keras.layers.Layer: def buildself, inputshape: self.kernel = self.addweight"kernel", 3, 3,...
CVE-2026-55687
CVE-2026-55687 describes a stack-based out-of-bounds write in the Espressif ESF-IDF JPEG decoder marker parsing (jpeg_parse_dqt_marker). The attack uses the attacker-controlled DQT marker Tq nibble as an index into the qt_tbl array without validating it is within 0..3, enabling malformed JPEG inp...
PYSEC-2026-3141 Core dump when loading TFLite models with quantization in TensorFlow
Impact Certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could be greater than 1 but code was always assuming sub-unit scaling. Thus, since code was calling...
PYSEC-2026-3299 Core dump when loading TFLite models with quantization in TensorFlow
Impact Certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could be greater than 1 but code was always assuming sub-unit scaling. Thus, since code was calling...
CVE-2026-5757
A flaw was found in Ollama's model quantization engine. An unauthenticated remote attacker can exploit this vulnerability to read and exfiltrate the server's heap memory. This could lead to sensitive data exposure, further compromise of the system, and allow for stealthy persistence within the...
PYSEC-2026-1031 TensorFlow vulnerable to `CHECK` fail in `FakeQuantWithMinMaxVarsGradient`
Impact When tf.quantization.fakequantwithminmaxvarsgradient receives input min or max that is nonscalar, it gives a CHECK fail that can trigger a denial of service attack. python import tensorflow as tf import numpy as np arg0=tf.constantvalue=np.random.randomsize=2, 2, shape=2, 2, dtype=tf.float...
PYSEC-2026-965 TensorFlow segfault TFLite converter on per-channel quantized transposed convolutions
Impact When converting transposed convolutions using per-channel weight quantization the converter segfaults and crashes the Python process. python import tensorflow as tf class QuantConv2DTransposedtf.keras.layers.Layer: def buildself, inputshape: self.kernel = self.addweight"kernel", 3, 3,...
PYSEC-2026-972 Core dump when loading TFLite models with quantization in TensorFlow
Impact Certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could be greater than 1 but code was always assuming sub-unit scaling. Thus, since code was calling...
CVE-2026-5757
Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence...
CVE-2026-5757
CVE-2026-5757 concerns Ollama’s model quantization engine. The CERT entry describes an unauthenticated remote information-disclosure vulnerability triggered via the model upload interface. Root cause: three factors—no bounds checking on user-supplied GGUF header metadata, unsafe memory access usi...
CVE-2026-5757
Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence...
EUVD-2026-39786
Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence...
CVE-2026-5757 There exists an unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine
Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence...
CVE-2026-5757 There exists an unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine
Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence...
vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
Summary 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 torch::empty uninitialized memory, but the dequantize CUDA kernel processes only a truncated...
Widening the Gap: Exploiting LLM Quantization Via Outlier Injection
LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existin...
