Laura Pullum

Laura L. Pullum

Reinforcement learning has received significant interest in recent years, due primarily to the successes of deep reinforcement learning at solving many challenging tasks such as playing Chess, Go and online computer games. However, with the increasing focus on reinforcement learning, applications outside of gaming and simulated environments require understanding the robustness, stability, and resilience of reinforcement learning methods. To this end, we conducted a comprehensive literature review to characterize the available literature on these three behaviors as they pertain to reinforcement learning. We classify the quantitative and theoretical approaches used to indicate or measure robustness, stability, and resilience behaviors. In addition, we identified the action or event to which the quantitative approaches were attempting to be stable, robust, or resilient. Finally, we provide a decision tree useful for selecting metrics to quantify the behaviors. We believe that this is the first comprehensive review of stability, robustness and resilience specifically geared towards reinforcement learning.

Sumit Kumar Jha, Susmit Jha, Rickard Ewetz et al.

Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model. These attacks can potentially leak private or proprietary data. We present a new extension of Fano's inequality and employ it to theoretically establish that the probability of success for a membership inference attack on a deep neural network can be bounded using the mutual information between its inputs and its activations. This enables the use of mutual information to measure the susceptibility of a DNN model to membership inference attacks. In our empirical evaluation, we show that the correlation between the mutual information and the susceptibility of the DNN model to membership inference attacks is 0.966, 0.996, and 0.955 for CIFAR-10, SVHN and GTSRB models, respectively.

Theodore Papamarkou, Hayley Guy, Bryce Kroencke et al.

Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of corrosion, including iron oxide discoloration, pitting and stress corrosion cracking, in dry storage stainless steel canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel.