Defending Against Machine Learning Based Inference Attacks via Adversarial Examples: Opportunities and Challenges

Abstract

As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker has access to some data (called public data) of an individual, a software, or a system; and the attacker uses an ML classifier to automatically infer their private data. Inference attacks pose severe privacy and security threats to individuals and systems. Inference attacks are successful because private data are statistically correlated with public data, and ML classifiers can capture such statistical correlations. In this chapter, we discuss the opportunities and challenges of defending against ML-equipped inference attacks via adversarial examples. Our key observation is that attackers rely on ML classifiers in inference attacks. The adversarial machine learning community has demonstrated that ML classifiers have various vulnerabilities. Therefore, we can turn the vulnerabilities of ML into defenses against inference attacks. For example, ML classifiers are vulnerable to adversarial examples, which add carefully crafted noise to normal examples such that an ML classifier makes predictions for the examples as we desire. To defend against inference attacks, we can add carefully crafted noise into the public data to turn them into adversarial examples, such that attackers' classifiers make incorrect predictions for the private data. However, existing methods to construct adversarial examples are insufficient because they did not consider the unique challenges and requirements for the crafted noise at defending against inference attacks. In this chapter, we take defending against inference attacks in online social networks as an example to illustrate the opportunities and challenges.

Federated Learning With Highly Imbalanced Audio Data

“…This approach is shown to produce less noisy results between rounds, but also takes longer to converge than the updates described in Equation 1. There is also the potential of reduced privacy, in that parameters related to particular clients are retained on the server, rather than being removed immediately following calculation of the new global model, which could conceivably allow, for instance, inference attacks [8].…”

MemGuard

“…Therefore, attackers who rely on machine learning also share its vulnerabilities and we can exploit such vulnerabilities to defend against them. For instance, we can leverage adversarial examples to mislead attackers who use machine learning classifiers to perform automated inference attacks [27]. One key challenge in this research direction is how to extend existing adversarial example methods to address the unique challenges of privacy protection.…”

Applications of Game Theory and Advanced Machine Learning Methods for Adaptive Cyberdefense Strategies in the Digital Music Industry

“…To be more exact, the energy that the player will pick at each narrative stage is determined by the strategy used in a game with just one player and repeated steps. e action must be feasible; that is, it must belong to all the available options of the gaming stage [24,25].…”

“…is was done because the large number of visitors combined with the enormous amounts of music content spent on a daily basis creates a new landscape of threats, in which the clear strategies for cybersecurity need to be rearranged on an ongoing basis. According to this logic, they frequently employ advanced techniques, including zero-day attacks, to launch attacks on music streaming platforms that modern cybercriminals have targeted [24,27,28].…”