Search for: All records

Existing adversarial algorithms for Deep Reinforcement Learning (DRL) have largely focused on identifying an optimal time to attack a DRL agent. However, little work has been explored in injecting efficient adversarial perturbations in DRL environments. We propose a suite of novel DRL adversarial attacks, called ACADIA, representing AttaCks Against Deep reInforcement leArning. ACADIA provides a set of efficient and robust perturbation-based adversarial attacks to disturb the DRL agent's decision-making based on novel combinations of techniques utilizing momentum, ADAM optimizer (i.e., Root Mean Square Propagation, or RMSProp), and initial randomization. These kinds of DRL attacks with novel integration of such techniques have not been studied in the existing Deep Neural Networks (DNNs) and DRL research. We consider two well-known DRL algorithms, Deep-Q Learning Network (DQN) and Proximal Policy Optimization (PPO), under Atari games and MuJoCo where both targeted and non-targeted attacks are considered with or without the state-of-the-art defenses in DRL (i.e., RADIAL and ATLA). Our results demonstrate that the proposed ACADIA outperforms existing gradient-based counterparts under a wide range of experimental settings. ACADIA is nine times faster than the state-of-the-art Carlini & Wagner (CW) method with better performance under defenses of DRL. 

Molybdenum oxide thin films are successfully deposited using spatial atomic layer deposition (SALD), a tool designed for high‐throughput industrial film growth. The structural and optical properties of the film are evaluated using ultraviolet photoelectron spectroscopy, high‐resolution transmission electron microscopy, and spectroscopic ellipsometry. To demonstrate the applicability of molybdenum oxide in industrial settings the films are applied as hole‐selective silicon heterojunction contacts for solar cells. When paired with intrinsic amorphous silicon passivation layers, implied open‐circuit voltages of 699 mV are achieved. The carrier transport is unaffected by low‐temperature contact anneals up to 300 °C with contact resistivities of ≈ 10 mΩ cm². Finally, the optical performance of silicon solar cells featuring different front hole‐selective heterojunction structures are simulated. It is shown that the generation current density of heterojunction solar cells can be significantly increased with the addition of SALD molybdenum oxide contacts.