Timezone: »

 
Adversarial poisoning attacks on reinforcement learning-driven energy pricing
Sam Gunn · Doseok Jang · Orr Paradise · Lucas Spangher · Costas J Spanos

Reinforcement learning (RL) has emerged as a strong candidate for implementing complex controls in energy systems, such as energy pricing in microgrids. But what happens when some of the microgrid controllers are compromised by a malicious entity? We demonstrate a novel attack in RL.Our attack perturbs each trajectory to reverse the direction of the estimated gradient. We demonstrate that if data from a small fraction of microgrid controllers is adversarially perturbed, the learning of the RL agent can be significantly slowed or (with larger perturbations) caused to operate at a loss. Prosumers also face higher energy costs, use their batteries less, and suffer from higher peak demand when the pricing aggregator is adversarially poisoned. We address this vulnerability with a “defense” module; i.e., a ``robustification'' of RL algorithms against this attack. Our defense identifies the trajectories with the largest influence on the gradient and removes them from the training data.

Author Information

Sam Gunn (UC Berkeley)
Doseok Jang (University of California, Berkeley)
Orr Paradise (University of California, Berkeley)
Lucas Spangher (UC Berkeley)
Costas J Spanos (University of California, Berkeley)

COSTAS J. SPANOS received the EE Diploma from the National Technical University of Athens, Greece in 1980 and the M.S. and Ph.D. degrees in ECE from Carnegie Mellon University in 1981 and 1985, respectively. In 1988 he joined the Faculty at the department of Electrical Engineering and Computer Sciences of the University of California at Berkeley. He has served as the Director of the Berkeley Microlab, the Associate Dean for Research in the College of Engineering and as the Chair of the Department of EECS. He works in statistical analysis in the design and fabrication of integrated circuits, and on novel sensors and computer-aided techniques in semiconductor manufacturing. He also works on statistical data mining techniques for energy efficiency applications. He has participated in two successful startup companies, Timbre Tech, (acquired by Tokyo Electron) and OnWafer Technologies (acquired by KLA-Tencor). He is presently the Director of the Center of Information Technology Research in the Interest of Society (CITRIS) and the Chief Technical Officer for the Berkeley Educational Alliance for Research in Singapore (BEARS).

More from the Same Authors