Skip to main content

Table 3 Summary for the attributes of diverse attacking method

From: Adversarial attack and defense in reinforcement learning-from AI security view

Method Black/White box Parameters Target algorithm Learning Examples generated Application scenario Attack effect
FGSM (Goodfellow et al. 2014a) White Box θ,x,y None One shot True Atari Game Taking wrong action
SPA (Xiang et al. 2018) White Box VQ,Pstart Q-Learning One shot True Path Planning No normal path planning
WBA (Bai et al. 2018) White Box VQ,x DQN One shot True Path Planning No normal path planning
CDG (Chen et al. 2018b) White Box V,x A3C One shot True Path Planning Unable to reach destination/Time increased
PIA (Behzadan and Munir 2017) Black Box None DQN Iterative True Atari Game Taking wrong action
STA (Lin et al. 2017) Black Box None None Iterative True Atari Game Taking wrong action
EA (Lin et al. 2017) Black Box None None Iterative True Atari Game Taking wrong action
AVI (Liu et al. 2017) Black Box None VIN One shot True Path Planning No normal path planning
  1. The Parameters denotes the parameters utilized for calculating the perturbations, Learning denotes the learning style for each attack method