TY - GEN
T1 - Feedback-Control Based Adversarial Attacks on Recurrent Neural Networks
AU - Deka, Shankar A.
AU - Stipanovic, Dusan M.
AU - Tomlin, Claire J.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/14
Y1 - 2020/12/14
N2 - Crafting adversarial inputs for attacks on neural networks and robustification against such attacks have continued to be a topic of keen interest in the machine learning community. Yet, the vast majority of work in current literature is only empirical in nature. We present a novel viewpoint on adversarial attacks on recurrent neural networks (RNNs) through the lens of dynamical systems theory. In particular, we show how control theory-based analysis tools can be leveraged to compute these adversarial input disturbances, and obtain bounds on how they impact the neural network performance. The disturbances are computed dynamically at each time-step by taking advantage of the recurrent architecture of RNNs, thus making them more efficient compared to prior work, as well as amenable to 'real-time' attacks. Finally, the theoretical results are supported by some illustrative examples.
AB - Crafting adversarial inputs for attacks on neural networks and robustification against such attacks have continued to be a topic of keen interest in the machine learning community. Yet, the vast majority of work in current literature is only empirical in nature. We present a novel viewpoint on adversarial attacks on recurrent neural networks (RNNs) through the lens of dynamical systems theory. In particular, we show how control theory-based analysis tools can be leveraged to compute these adversarial input disturbances, and obtain bounds on how they impact the neural network performance. The disturbances are computed dynamically at each time-step by taking advantage of the recurrent architecture of RNNs, thus making them more efficient compared to prior work, as well as amenable to 'real-time' attacks. Finally, the theoretical results are supported by some illustrative examples.
UR - http://www.scopus.com/inward/record.url?scp=85099882892&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099882892&partnerID=8YFLogxK
U2 - 10.1109/CDC42340.2020.9303949
DO - 10.1109/CDC42340.2020.9303949
M3 - Conference contribution
AN - SCOPUS:85099882892
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 4677
EP - 4682
BT - 2020 59th IEEE Conference on Decision and Control, CDC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 59th IEEE Conference on Decision and Control, CDC 2020
Y2 - 14 December 2020 through 18 December 2020
ER -