Conflicting Interactions Among Protections Mechanisms for Machine Learning Models

07/05/2022
by   Sebastian Szyller, et al.
6

Nowadays, systems based on machine learning (ML) are widely used in different domains. Given their popularity, ML models have become targets for various attacks. As a result, research at the intersection of security and privacy, and ML has flourished. The research community has been exploring the attack vectors and potential mitigations separately. However, practitioners will likely need to deploy defences against several threats simultaneously. A solution that is optimal for a specific concern may interact negatively with solutions intended to address other concerns. In this work, we explore the potential for conflicting interactions between different solutions that enhance the security/privacy of ML-base systems. We focus on model and data ownership; exploring how ownership verification techniques interact with other ML security/privacy techniques like differentially private training, and robustness against model evasion. We provide a framework, and conduct systematic analysis of pairwise interactions. We show that many pairs are incompatible. Where possible, we provide relaxations to the hyperparameters or the techniques themselves that allow for the simultaneous deployment. Lastly, we discuss the implications and provide guidelines for future work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/29/2019

SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
research
01/12/2022

When Machine Learning Meets Spectrum Sharing Security: Methodologies and Challenges

The exponential growth of internet connected systems has generated numer...
research
08/22/2022

SoK: Machine Learning with Confidential Computing

Privacy and security challenges in Machine Learning (ML) have become a c...
research
12/18/2022

A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness

Speech-centric machine learning systems have revolutionized many leading...
research
03/20/2022

The Dark Side: Security Concerns in Machine Learning for EDA

The growing IC complexity has led to a compelling need for design effici...
research
09/11/2023

Privacy Side Channels in Machine Learning Systems

Most current approaches for protecting privacy in machine learning (ML) ...
research
10/12/2020

Security and Privacy Considerations for Machine Learning Models Deployed in the Government and Public Sector (white paper)

As machine learning becomes a more mainstream technology, the objective ...

Please sign up or login with your details

Forgot password? Click here to reset