Deepfakes – essentially putting words in someone else’s mouth in a very believable way – are becoming more sophisticated by the day and increasingly hard to spot. Recent examples of deepfakes include Taylor Swift nude images, an audio recording of President Joe Biden telling New Hampshire residents not to vote, and a video of Ukrainian President Volodymyr Zelenskyy calling on his troops to lay down their arms.

Although companies have created detectors to help spot deepfakes, studies have found that biases in the data used to train these tools can lead to certain demographic groups being unfairly targeted.

My team and I discovered new methods that improve both the fairness and the accuracy of the algorithms used to detect deepfakes.

To do so, we used a large dataset of facial forgeries that lets researchers like us train our deep-learning approaches. We built our work around the state-of-the-art Xception detection algorithm, which is a widely used foundation for deepfake detection systems and can detect deepfakes with an accuracy of 91.5%.

We created two separate deepfake detection methods intended to encourage fairness.

One was focused on making the algorithm more aware of demographic diversity by labeling datasets by gender and race to minimize errors among underrepresented groups.

The other aimed to improve fairness without relying on demographic labels by focusing instead on features not visible to the human eye.

It turns out the first method worked best. It increased accuracy rates from the 91.5% baseline to 94.17%, which was a bigger increase than our second method as well as several others we tested. Moreover, it increased accuracy while enhancing fairness, which was our main focus.

We believe fairness and accuracy are crucial if the public is to accept artificial intelligence technology. When large language models like ChatGPT “hallucinate,” they can perpetuate erroneous information. This affects public trust and safety.

Likewise, deepfake images and videos can undermine the adoption of AI if they cannot be quickly and accurately detected. Improving the fairness of these detection algorithms so that certain demographic groups aren’t disproportionately harmed by them is a key aspect to this.

Our research addresses deepfake detection algorithms’ fairness, rather than just attempting to balance the data. It offers a new approach to algorithm design that considers demographic fairness as a core aspect.

Share:
More In Technology
Albania’s prime minister appoints an AI-generated ‘minister’ to tackle corruption
Albania's Prime Minister Edi Rama says his new Cabinet will include an artificial intelligence “minister” in charge of fighting corruption. The AI, named Diella, will oversee public funding projects and combat corruption in public tenders. Diella was launched earlier this year as a virtual assistant on the government's public service platform. Corruption has been a persistent issue in Albania since 1990. Rama's Socialist Party won a fourth consecutive term in May. It aims to deliver EU membership for Albania in five years, but the opposition Democratic Party remains skeptical.
Klarna shares jump 30% on Wall Street debut
Swedish buy now, pay later company Klarna is making its highly anticipated public debut on the New York Stock Exchange Wednesday, the latest in a run of high-profile initial public offerings this year. The offering priced at $40 Tuesday, above the forecasted range of $35 to $37 a share, valuing the company at more than $15 billion. The valuation easily makes Klarna one of the biggest IPOs so far in 2025, which has been one of the busier years for companies going public. Other popular IPOs so far this year include the design software company Figma and Circle Internet Group, which issues the USDC stablecoin..
Musk loses crown as world’s richest to software giant Larry Ellison
Oracle co-founder Larry Ellison wrested the title of the world’s richest man from longtime holder Elon Musk early Wednesday as stock in his software giant rocketed more than a third in a stunning few minutes of trading. That is according to wealth tracker Bloomberg. A college dropout, the 81-year-old Ellison is now worth $393 billion, Bloomberg says, several billion more than Musk, who had been the world’s richest for four years. The switch in the ranking came after a blockbuster earnings report from Oracle. Forbes still has Musk as the richest, however, valuing his private businesses much higher.
Load More