TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
因为老板之后可能要做深度学习框架的模糊测试，所以把之前一直没啃的paper先啃了。。 摘要 本文开发一个对神经网络的 coverage-guided fuzzing(CGF) 方法。然后讨论应用CGF达到以下目标：找到预训练好的神经网络中的数值型错误，生成神经网络的不一致并找到这些版本的神经网络，发现字符级别语言模型中意想不到的行为。最后开源了这个工具。 1. 绪论 机器学习模型由于下述原因很难d
相关文章
- 1. [论文解读]TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
- 2. Few-shot Learning with Graph Neural Networks
- 3. Brain tumor segmentation with Deep Neural Networks
- 4. ImageNet Classification with Deep Convolutional Neural Networks
- 5. Convolutional Neural Networks with Alternately Updated Clique
- 6. Few-Shot Learning with Graph Neural Networks
- 7. Overlapping Community Detection with Graph Neural Networks
- 8. How to Implement Neural Networks with TensorFlow
- 9. Balanced Binary Neural Networks With Gated Residual
- 10. AlexNet：ImageNet Classification with Deep Convolutional Neural Networks
- 更多相关文章...
- • XSLT
- • PHP error_log() 函数 - PHP参考手册
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
- • 算法总结-股票买卖
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. [论文解读]TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
- 2. Few-shot Learning with Graph Neural Networks
- 3. Brain tumor segmentation with Deep Neural Networks
- 4. ImageNet Classification with Deep Convolutional Neural Networks
- 5. Convolutional Neural Networks with Alternately Updated Clique
- 6. Few-Shot Learning with Graph Neural Networks
- 7. Overlapping Community Detection with Graph Neural Networks
- 8. How to Implement Neural Networks with TensorFlow
- 9. Balanced Binary Neural Networks With Gated Residual
- 10. AlexNet：ImageNet Classification with Deep Convolutional Neural Networks