no code implementations • 19 Mar 2024 • Ilya Yegorov, Eli Kobrin, Darya Parygina, Alexey Vishnyakov, Andrey Fedotov
To identify the most vulnerable parts of the machine learning frameworks, we analyze their potential attack surfaces and develop fuzz targets for PyTorch, TensorFlow, and related projects such as h5py.
3 code implementations • 18 Nov 2020 • Alexey Vishnyakov, Andrey Fedotov, Daniil Kuts, Alexander Novikov, Darya Parygina, Eli Kobrin, Vlada Logunova, Pavel Belecky, Shamil Kurmangaleev
Sydr performs inversion of branches in path predicate.
Cryptography and Security