Artificial intelligence content detection

In a study conducted by Weber-Wulff et al., and published in 2023, researchers evaluated 14 detection tools including Turnitin and GPT Zero, and found that "all scored below 80% of accuracy and only 5 over 70%.

[16] An article by Thomas Germain, published on Gizmodo in June 2024, reported job losses among freelance writers and journalists due to AI text detection software mistakenly classifying their work as AI-generated.

This watermarking approach allows content to be flagged as AI-generated with a high level of accuracy, even when text is slightly paraphrased or modified.

However, while promising, watermarking faces challenges in remaining robust under adversarial transformations and ensuring compatibility across different LLMs.

The authors outline a range of adversarial tactics, including text insertion, deletion, and substitution attacks, that could be used to bypass watermark detection.

These attacks vary in complexity, from simple paraphrasing to more sophisticated approaches involving tokenization and homoglyph alterations.

The study highlights the challenge of maintaining watermark robustness against attackers who may employ automated paraphrasing tools or even specific language model replacements to alter text spans iteratively while retaining semantic similarity.

Experimental results show that although such attacks can degrade watermark strength, they also come at the cost of text quality and increased computational resources.