Advances in adversarial attacks and defenses in computer vision: A survey

N Akhtar, A Mian, N Kardan, M Shah - IEEE Access, 2021‏ - ieeexplore.ieee.org
Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

Robust reinforcement learning: A review of foundations and recent advances

J Moos, K Hansel, H Abdulsamad, S Stark… - Machine Learning and …, 2022‏ - mdpi.com
Reinforcement learning (RL) has become a highly successful framework for learning in
Markov decision processes (MDP). Due to the adoption of RL in realistic and complex …

Deep reinforcement learning for smart grid operations: Algorithms, applications, and prospects

Y Li, C Yu, M Shahidehpour, T Yang… - Proceedings of the …, 2023‏ - ieeexplore.ieee.org
With the increasing penetration of renewable energy and flexible loads in smart grids, a
more complicated power system with high uncertainty is gradually formed, which brings …

[PDF][PDF] Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification

S Wang, H Zhang, K Xu, X Lin, S Jana… - Advances in neural …, 2021‏ - proceedings.neurips.cc
Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …

Threat of adversarial attacks on deep learning in computer vision: A survey

N Akhtar, A Mian - Ieee Access, 2018‏ - ieeexplore.ieee.org
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

Robust reinforcement learning using offline data

K Panaganti, Z Xu, D Kalathil… - Advances in neural …, 2022‏ - proceedings.neurips.cc
The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the
uncertainty in model parameters. Parameter uncertainty commonly occurs in many real …

Rorl: Robust offline reinforcement learning via conservative smoothing

R Yang, C Bai, X Ma, Z Wang… - Advances in neural …, 2022‏ - proceedings.neurips.cc
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount
of offline data for complex decision-making tasks. Due to the distribution shift issue, current …

Resilient machine learning for networked cyber physical systems: A survey for machine learning security to securing machine learning for CPS

FO Olowononi, DB Rawat, C Liu - … Communications Surveys & …, 2020‏ - ieeexplore.ieee.org
Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and
information or cyber worlds. Their deployment in critical infrastructure have demonstrated a …

Robust reinforcement learning on state observations with learned optimal adversary

H Zhang, H Chen, D Boning, CJ Hsieh - arxiv preprint arxiv:2101.08452, 2021‏ - arxiv.org
We study the robustness of reinforcement learning (RL) with adversarially perturbed state
observations, which aligns with the setting of many adversarial attacks to deep …

Recurrent model-free rl can be a strong baseline for many pomdps

T Ni, B Eysenbach, R Salakhutdinov - arxiv preprint arxiv:2110.05038, 2021‏ - arxiv.org
Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit
assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with …