DeepAI AI Chat
Log In Sign Up

Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems

by   Lars Fischer, et al.

This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performance indicators of the system. Our concept provides adaptive, repeatable, actor-based testing with a chance of detecting previously unknown attack vectors. We provide the constitutive nomenclature of ARL and, based on it, the description of experimental setups and results of a preliminary implementation of ARL in simulated power systems.


page 1

page 2

page 3

page 4


Models and Framework for Adversarial Attacks on Complex Adaptive Systems

We introduce the paradigm of adversarial attacks that target the dynamic...

Geometric algorithms for predicting resilience and recovering damage in neural networks

Biological neural networks have evolved to maintain performance despite ...

Resilience of Well-structured Graph Transformation Systems

Resilience is a concept of rising interest in computer science and softw...

Leveraging Decentralized Artificial Intelligence to Enhance Resilience of Energy Networks

This paper reintroduces the notion of resilience in the context of recen...

Evaluating Resilience of Encrypted Traffic Classification Against Adversarial Evasion Attacks

Machine learning and deep learning algorithms can be used to classify en...

Soccer: a quantitative analysis of team resilience and the miracle of Bern

Resilience is the ability to positively respond to adversity. It has bee...

Managing contextual artificial neural networks with a service-based mediator

Today, a wide variety of probabilistic and expert AI systems used to ana...