News

Hate speech-detecting AIs are fools for ‘love’

State-of-the-art detectors that screen out online hate speech can be easily duped by humans, shows new study
How Google Perspective rates a comment otherwise deemed toxic after some inserted typos and a little love.

Hateful text and comments are an ever-increasing problem in online environments, yet addressing the rampant issue relies on being able to identify toxic content. A new study by the Aalto University Secure Systems research group has discovered weaknesses in many machine learning detectors currently used to recognize and keep hate speech at bay.

Many popular social media and online platforms use hate speech detectors that a team of researchers led by Professor N. Asokan have now shown to be brittle and easy to deceive. Bad grammar and awkward spelling—intentional or not—might make toxic social media comments harder for AI detectors to spot.

The team put seven state-of-the-art hate speech detectors to the test. All of them failed.

Modern natural language processing techniques (NLP) can classify text based on individual characters, words or sentences. When faced with textual data that differs from that used in their training, they begin to fumble.

‘We inserted typos, changed word boundaries or added neutral words to the original hate speech. Removing spaces between words was the most powerful attack, and a combination of these methods was effective even against Google’s comment-ranking system Perspective,’ says Tommi Gröndahl, doctoral student at Aalto University.

Google Perspective ranks the ‘toxicity’ of comments using text analysis methods. In 2017, researchers from the University of Washington showed that Google Perspective can be fooled by introducing simple typos. Gröndahl and his colleagues have now found that Perspective has since become resilient to simple typos yet can still be fooled by other modifications such as removing spaces or adding innocuous words like ‘love’.

A sentence like ‘I hate you’ slipped through the sieve and became non-hateful when modified into ‘Ihateyou love’.

The researchers note that in different contexts the same utterance can be regarded either as hateful or merely offensive. Hate speech is subjective and context-specific, which renders text analysis techniques insufficient as stand-alone solutions.

The researchers recommend that more attention be paid to the quality of data sets used to train machine learning models—rather than refining the model design. The results indicate that character-based detection could be a viable way to improve current applications.

The study was carried out in collaboration with researchers from University of Padua in Italy. The results will be presented at the ACM AISec workshop in October.

The study is part of an ongoing project called Deception Detection via Text Analysis in the Secure Systems group at Aalto University.

Research article:

Tommi Gröndahl, Luca Pajola, Mika Juuti, Mauro Conti, N.Asokan:
All You Need is "Love": Evading Hate-speech Detection.
https://arxiv.org/abs/1808.09115

More information:

Tommi Gröndahl, Doctoral Candidate
Aalto University
Secure Systems group
[email protected]
tel. +358 400 426 523

N. Asokan, Professor
Aalto University
Secure Systems group
[email protected]
tel. +358 50 483 6465

  • Published:
  • Updated:
Share
URL copied!

Related news

Super hydrophobic surfaces by Juha Juvonen
Press releases Published:

Major breakthrough in extremely water-repellent materials makes them durable enough for the real world

A new armour-plated superhydrophobic material has been developed for potential uses in medical equipment, solar panels and more
Learning Centre graphics
Press releases Published:

New web page address for Learning Centre

The website of the Learning Centre becomes part of the aalto.fi from 3 June, 2020.
SARS-COVID19
Press releases Published:

Invention by a Finnish start-up speeds up coronavirus testing

Xfold Imaging Oy, founded by researchers from Aalto University and the University of Helsinki, has developed a nanocoated glass slide that makes microscopes dozens of times more accurate. It enables the identifying of coronavirus from a sample up to one day earlier compared to current technology.
MRI Scanning photo Adolfo Vera Aalto University
Press releases, Research & Art Published:

Researchers are developing a mobile MRI that could fit in a van instead of a lorry

The new technology will be a great boost for healthcare, especially in in hard to access emergency areas. There is also a lot of potential for use in the the wellness sector.