all InfoSec news
How to Train your Antivirus: RL-based Hardening through the Problem-Space
March 1, 2024, 5:11 a.m. | Jacopo Cortellazzi, Ilias Tsingenopoulos, Branislav Bo\v{s}ansk\'y, Simone Aonzo, Davy Preuveneers, Wouter Joosen, Fabio Pierazzi, Lorenzo Cavallaro
cs.CR updates on arXiv.org arxiv.org
Abstract: ML-based malware detection on dynamic analysis reports is vulnerable to both evasion and spurious correlations. In this work, we investigate a specific ML architecture employed in the pipeline of a widely-known commercial antivirus company, with the goal to harden it against adversarial malware. Adversarial training, the sole defensive technique that can confer empirical robustness, is not applicable out of the box in this domain, for the principal reason that gradient-based perturbations rarely map back to …
adversarial analysis antivirus architecture arxiv commercial cs.ai cs.cr detection dynamic dynamic analysis evasion goal hardening malware malware detection pipeline problem reports space train training vulnerable work
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
1 day, 5 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
1 day, 5 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Data & Security Engineer Lead
@ LiquidX | Singapore, Central Singapore, Singapore
IT and Cyber Risk Control Lead
@ GXS Bank | Singapore - OneNorth
Consultant Senior en Gestion de Crise Cyber et Continuité d’Activité H/F
@ Hifield | Sèvres, France
Cyber Security Analyst (Weekend 1st Shift)
@ Fortress Security Risk Management | Cleveland, OH, United States
Senior Manager, Cybersecurity
@ BlueTriton Brands | Stamford, CT, US