Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning

Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Avisek Naug, Sahand Ghorbanpour

AAAI 2024 pp. 23829-23831

doi:10.1609/AAAI.V38I21.30579 /aaai/2024/sarkar2024aaai-robustness/

Abstract

We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework focuses on identifying sensitive regions and inducing misclassifications with minimal distortions and various distortion types. The novel RL method outperforms state-of-the-art methods for all three applications, proving its efficiency. Our RL approach produces superior localization masks, enhancing interpretability for image classification and ECG analysis models. For applications such as ECG analysis, our platform highlights critical ECG segments for clinicians while ensuring resilience against prevalent distortions. This comprehensive tool aims to bolster both resilience with adversarial training and transparency across varied applications and data types.

PDF AAAI Semantic Scholar

Cite

Text

Sarkar et al. "Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30579

Markdown

[Sarkar et al. "Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/sarkar2024aaai-robustness/) doi:10.1609/AAAI.V38I21.30579

BibTeX

@inproceedings{sarkar2024aaai-robustness,
  title     = {{Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning}},
  author    = {Sarkar, Soumyendu and Babu, Ashwin Ramesh and Mousavi, Sajad and Gundecha, Vineet and Naug, Avisek and Ghorbanpour, Sahand},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23829-23831},
  doi       = {10.1609/AAAI.V38I21.30579},
  url       = {https://mlanthology.org/aaai/2024/sarkar2024aaai-robustness/}
}