Weeding out Fake News


New research reveals biases in fake news datasets and improves the use of automatic detectors.

MIT News

To prove this, the researchers developed attacks that they showed could fool state-of-the-art fake-news detectors. Since the detector thinks that the human-written text is real, the attacker cleverly (and automatically) impersonates such text. In addition, because the detector thinks the machine-generated text is fake, it might be forced to also falsely condemn totally legitimate uses of automatic text generation.

MIT News