all InfoSec news
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Feb. 28, 2024, 5:11 a.m. | Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
cs.CR updates on arXiv.org arxiv.org
Abstract: We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition. The main contributions of this work are an impossibility result and an achievability result for backdoor detection. We show a no-free-lunch theorem, proving that universal (adversary-unaware) backdoor detection is impossible, except for very small alphabet sizes. Thus, we argue, …
arxiv backdoor cs.ai cs.cr cs.lg definition detection machine machine learning main problem problems stat.ml systems testing utility work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Junior Cybersecurity Analyst - 3346195
@ TCG | 725 17th St NW, Washington, DC, USA
Cyber Intelligence, Senior Advisor
@ Peraton | Chantilly, VA, United States
Consultant Cybersécurité H/F - Innovative Tech
@ Devoteam | Marseille, France
Manager, Internal Audit (GIA Cyber)
@ Standard Bank Group | Johannesburg, South Africa
Staff DevSecOps Engineer
@ Raft | San Antonio, TX (Local Remote)
Domain Leader Cybersecurity
@ Alstom | Bengaluru, KA, IN