Injecting around 50 poisoned samples with a stealthy trigger creates backdoors in deep learning models achieving over 90% attack success under a weak threat model with no model or data knowledge required.
Mastering the game of go with deep neural networks and tree search
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Develops a distributed primal-dual actor-critic method for constrained multi-agent RL with general parameterization, proves consensus and convergence to an equilibrium, analyzes sub-optimality, and introduces a constrained Cournot game testbed.
Iterative temporal differencing with fixed random synaptic feedback can replace the activation function derivative in error backpropagation.
citing papers explorer
-
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Injecting around 50 poisoned samples with a stealthy trigger creates backdoors in deep learning models achieving over 90% attack success under a weak threat model with no model or data knowledge required.
-
A Distributed Primal-Dual Method for Constrained Multi-agent Reinforcement Learning with General Parameterization
Develops a distributed primal-dual actor-critic method for constrained multi-agent RL with general parameterization, proves consensus and convergence to an equilibrium, analyzes sub-optimality, and introduces a constrained Cournot game testbed.
-
Iterative temporal differencing with random synaptic feedback weights support error backpropagation for deep learning
Iterative temporal differencing with fixed random synaptic feedback can replace the activation function derivative in error backpropagation.