# Manipulating hidden-Markov-model inferences by corrupting batch data

arXiv: https://arxiv.org/abs/2402.13287 · HTML: https://mlsanity.com/paper/2402.13287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning](https://mlsanity.com/paper/1804.00308/) (2018)
- [Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems](https://mlsanity.com/paper/1709.08071/) (2017)
- [Deep Neural Rejection against Adversarial Examples](https://mlsanity.com/paper/1910.00470/) (2019)
- [Adversarial Machine Learning in Network Intrusion Detection Systems](https://mlsanity.com/paper/2004.11898/) (2020)
- [Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid](https://mlsanity.com/paper/1708.06939/) (2017)
- [Support Vector Machines under Adversarial Label Contamination](https://mlsanity.com/paper/2206.00352/) (2022)
- [Adversarial Attacks on Probabilistic Autoregressive Forecasting Models](https://mlsanity.com/paper/2003.03778/) (2020)
- [FADER: Fast Adversarial Example Rejection](https://mlsanity.com/paper/2010.09119/) (2020)
- [Adversarial Machine Learning: Bayesian Perspectives](https://mlsanity.com/paper/2003.03546/) (2020)
- [Adversarial classification: An adversarial risk analysis approach](https://mlsanity.com/paper/1802.07513/) (2018)
- [Reinforcement Learning under Threats](https://mlsanity.com/paper/1809.01560/) (2018)
- [Optimal Attack against Autoregressive Models by Manipulating the Environment](https://mlsanity.com/paper/1902.00202/) (2019)
- [Adversarial attacks against Bayesian forecasting dynamic models](https://mlsanity.com/paper/2110.10783/) (2021)
- [Augmented Probability Simulation Methods for Sequential Games](https://mlsanity.com/paper/1910.04574/) (2019)

## Abstract (arXiv)

Time-series models typically assume untainted and legitimate streams of data. However, a self-interested adversary may have incentive to corrupt this data, thereby altering a decision maker's inference. Within the broader field of adversarial machine learning, this research provides a novel, probabilistic perspective toward the manipulation of hidden Markov model inferences via corrupted data. In particular, we provision a suite of corruption problems for filtering, smoothing, and decoding inferences leveraging an adversarial risk analysis approach. Multiple stochastic programming models are set forth that incorporate realistic uncertainties and varied attacker objectives. Three general solution methods are developed by alternatively viewing the problem from frequentist and Bayesian perspectives. The efficacy of each method is illustrated via extensive, empirical testing. The developed methods are characterized by their solution quality and computational effort, resulting in a stratification of techniques across varying problem-instance architectures. This research highlights the weaknesses of hidden Markov models under adversarial activity, thereby motivating the need for robustification techniques to ensure their security.