mlsanityData to 7 Oct 2026

Machine Learning Featurizations for AI Hacking of Political Systems

arXiv 2110.09231 ↗First posted 8 Oct 2021cs.CY cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

What would the inputs be to a machine whose output is the destabilization of a robust democracy, or whose emanations could disrupt the political power of nations? In the recent essay "The Coming AI Hackers," Schneier (2021) proposed a future application of artificial intelligences to discover, manipulate, and exploit vulnerabilities of social, economic, and political systems at speeds far greater than humans' ability to recognize and respond to such threats. This work advances the concept by applying to it theory from machine learning, hypothesizing some possible "featurization" (input specification and transformation) frameworks for AI hacking. Focusing on the political domain, we develop graph and sequence data representations that would enable the application of a range of deep learning models to predict attributes and outcomes of political, particularly legislative, systems. We explore possible data models, datasets, predictive tasks, and actionable applications associated with each framework. We speculate about the likely practical impact and feasibility of such models, and conclude by discussing their ethical implications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 65 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

21 of 65 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  3. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  4. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  6. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
  7. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  8. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  9. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  10. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  11. 2020A Brief Review of Domain Adaptationcited by 287
  12. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
9 more
  1. 2018An introduction to domain adaptation and transfer learningcited by 112
  2. 2021An Introduction to Deep Generative Modelingcited by 104
  3. 2021The AI Index 2021 Annual Reportcited by 34
  4. 2018Balanced Distribution Adaptation for Transfer Learningcited by 32
  5. 2021Production Machine Learning Pipelines: Empirical Analysis and Optimization Opportunitiescited by 21
  6. 2015Scalable Bayesian Inference for Excitatory Point Process Networkscited by 9
  7. 2021AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Riskscited by 6
  8. 2019Forecasting Transformative AI: An Expert Surveycited by 4
  9. 2020Deep Learning for Political Sciencecited by 3

Built on by

Not cited yet.