Towards Revealing Parallel Adversarial Attack on Politician Socialnet of Graph Structure

<div><i>k</i> influence on test statistics <svg height="8.68572pt" id="M339" style="vertical-align:-0.0498209pt" version="1.1" viewbox="-0.0498162 -8.6359 9.05107 8.68572" width="9.05107pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M671 0V28C608 36 593 47 562 130C495 309 432 486 368 665L336 656C270 481 202 311 134 139C98 47 84 39 20 28V0H241V28C167 38 156 47 178 115C217 236 276 383 327 530H329C375 398 437 223 484 92C499 47 489 37 424 28V0H671Z"></path></g></svg> value among different perturbation budgets <span class="nowrap"><svg height="8.68572pt" id="M340" style="vertical-align:-0.0498209pt" version="1.1" viewbox="-0.0498162 -8.6359 8.46388 8.68572" width="8.46388pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M600 0V24L339 665L311 657L43 24V0H600ZM497 50H107L303 539L497 50Z"></path></g></svg>.</span></div>

Security and Communication Networks

fig7

Figure 7

Figure 7: Towards Revealing Parallel Adversarial Attack on Politician Socialnet of Graph Structure 