SoylentNews

AI Sucks At Stopping Online Trolls Spewing Toxic Comments

posted by mrpg on Saturday September 01 2018, @07:01AM   
from the blame-humans-of-course dept.

Arthur T Knackerbracket writes:

A bot called Arthur has collected the following story from the RSS feeds:

New research has shown just how bad AI is at dealing with online trolls.

Such systems struggle to automatically flag nudity and violence, don’t understand text well enough to shoot down fake news and aren’t effective at detecting abusive comments from trolls hiding behind their keyboards.

A group of researchers from Aalto University and the University of Padua found this out when they tested seven state-of-the-art models used to detect hate speech. All of them failed to recognize foul language when subtle changes were made, according to a paper [PDF] on arXiv.

Adversarial examples can be created automatically by using algorithms to misspell certain words, swap characters for numbers or add random spaces between words or attach innocuous words such as ‘love’ in sentences.

The models failed to pick up on adversarial examples and successfully evaded detection. These tricks wouldn’t fool humans, but machine learning models are easily blindsighted. They can’t readily adapt to new information beyond what’s been spoonfed to them during the training process.

---

Original Submission

• Re:offense vs defense Re:offense vs defense (Score: 1, Touché) by Anonymous Coward on Saturday September 01 2018, @08:39AM (2 children)

  by Anonymous Coward on Saturday September 01 2018, @08:39AM (#729158)

  All software is pretty static. ... He can examine your code, poke it, prod it, kick it around, and watch what it does.

  Bullshit. All the crypto algos are public, NSA still needs to buy that $5 wrench to get to the encryption key.

  All this AI is just software, after all.

  Da fuck - most of this AI is in the model that one trains - i.e. data.

  You, the defender - the software writer - can improve your defensive fortress forever. That won't change the fact that the attackers have the initiative, and they are destined to beat you.

  1. Oh, wow! The attacker has the initiative. How insightful!
     Do you attend the local tautology club often?
  2. Perfect security does not exist. It is only a balance between the cost of the defender vs the cost of the attacker - if one is some good orders of magnitude lower than the other, that one will "win" most of the time. This is how cryptography works.

  Yes, you are right, today's AI is dumb and adversarial attacks are easy to craft. But you are right for the wrong (or intellectually bland) reasons.

  Parent

  Starting Score:	0		points
  Moderation		+1
  Touché=1, Total=1
  Extra 'Touché' Modifier		0
  Total Score:		1

• Re:offense vs defense Re:offense vs defense (Score: 0) by Anonymous Coward on Saturday September 01 2018, @09:50AM (1 child)

  by Anonymous Coward on Saturday September 01 2018, @09:50AM (#729182)

  nice warping you attempted there before conceding his point!

  "they are destined to beat you."

  the archetypal war between (ordered)day and (chaotic)night requires
  that we walk along the razors edge of culture without falling into the deep on either side.

  Parent

  • Re:offense vs defense (Score: 0) by Anonymous Coward on Saturday September 01 2018, @10:10AM

    by Anonymous Coward on Saturday September 01 2018, @10:10AM (#729189)

    His point is: "AI Sucks At Stopping Online Trolls Spewing Toxic Comments" with wrong explanations on why is that.
    Where the wrong explanations are relevant.
    Take a trained AI and go trial-and-error-hacker to find the cracks.
    Then find adversarial attacks based on the knowledge on NN and compare the costs between the two approaches.

    Parent