ProAPT: Projection of APT Threats with Deep Reinforcement Learning

no code implementations • 15 Sep 2022 • Motahareh Dehghan, Babak Sadeghiyan, Erfan Khosravian, Alireza Sedighi Moghaddam, Farshid Nooshi

As supervised and unsupervised learning methods require APT datasets for projecting the next step of APTs, they are unable to identify unknown APT threats.

reinforcement-learning Reinforcement Learning (RL)

A Secure Two-Party Computation Protocol for Intersection Detection between Two Convex Hulls

no code implementations • 31 Oct 2020 • Amirahmad Chapnevis, Babak Sadeghiyan

The experiments successfully found a secure protocol for intersection detection between two convex hulls in geometrical shapes such as the pyramid and cuboid.

Computational Geometry Cryptography and Security

Reconstruction of C&C Channel for P2P Botnet

no code implementations • 10 Apr 2019 • Mohammad Jafari Dehkordi, Babak Sadeghiyan

In our method, the probability of connections between bots is estimated by using the inaccurate receiving times of several cascades, network model parameters of C&C channel, and end-to-end delay distribution of the Internet.

Cryptography and Security