Frame-Level Temporal Difference Learning for Partial Deepfake Speech Detection

Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on detecting transition artifacts between bonafide and deepfake...

Hashed Watermark As a Filter: Defeating Forging and Overwriting Attacks in Weight-Based Neural Network Watermarking

As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking NNW as a promising solution. Among various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain vulnerable to...

AZL-35314 CVE-2023-25669 affecting package tensorflow for versions less than 2.11.1-1

TensorFlow is an open source platform for machine learning. Prior to versions 2.12.0 and 2.11.1, if the stride and window size are not positive for tf.rawops.AvgPoolGrad, it can give a floating point exception. A fix is included in TensorFlow version 2.12.0 and version 2.11.1...

GHSA-MGMH-G2V6-MQW5 TensorFlow vulnerable to `CHECK` failure in `AvgPoolOp`

Impact The AvgPoolOp function takes an argument ksize that must be positive but is not checked. A negative ksize can trigger a CHECK failure and crash the program. python import tensorflow as tf import numpy as np value = np.ones1, 1, 1, 1 ksize = 1, 1e20, 1, 1 strides = 1, 1, 1, 1 padding = 'SAM...

Google TensorFlow 安全漏洞

Google TensorFlow is an end-to-end open source platform for machine learning from Google, Inc. A denial-of-service vulnerability exists in Google TensorFlow, which stems from the AvgPoolOp function accepting a parameter ksize , which must be positive but is not checked. An attacker could exploit...

PYSEC-2021-703

TensorFlow is an end-to-end open source platform for machine learning. The implementation of tf.rawops.AvgPool3DGrad is vulnerable to a heap buffer overflow. The...