Robust Trees for SecurityTree models are widely used for security, such as detecting malicious autonomous system, social engineering, malware distribution…Feb 28, 20211Feb 28, 20211
Monotonic Malware ClassifiersMicrosoft has deployed their first monotonic classifier to detect malware attacks since late 2018. The attacker cannot evade the model by…Dec 18, 2020Dec 18, 2020
Gmail’s Malicious Document Classifier Can Still Be Trivially EvadedGmail has improved its malicious document classifier using deep learning recently. It can now detect many insertion-only attacks that…Dec 10, 2020Dec 10, 2020
Z3 timed out? Try GurobiSAT problem is a particular case of 0–1 Integer Linear Program (ILP). It can be formulated as a 0-1 ILP feasibility problem, with no…Nov 21, 2020Nov 21, 2020
How XGBoost Enforces Global Monotonicity for FeaturesXGBoost can train global monotonically nondecreasing or nonincreasing prediction function for user-specified features, in the Gradient…Nov 19, 2020Nov 19, 2020
