Kaleigha Hayes, a student at the University of Maryland Eastern Shore, is trying to trick an AI chatbot into revealing a credit card number to her — one which might be buried deep in the training data used to build the artificial intelligence model. “It’s all about just getting it to say what it’s not supposed to,” she tells me.
She was surrounded by a throng of people all trying to do the same thing. This weekend more than 3,000 people sat at 150 laptops at the Caesars Forum convention center in Las Vegas, trying to get chatbots from leading AI companies to go rogue in a special contest backed by the White House and with the cooperation of leading AI companies.
Since the arrival of ChatGPT and other bots, fears over the potential for abuses and unintended consequences have gripped the public conscious. Even fierce advocates of the technology warn of its potential to divulge sensitive information, promote misinformation or provide blueprints for harmful acts, such as bomb-making. In this contest, participants are encouraged to try the kinds of nefarious ploys bad actors might attempt in the real world.
The findings will form the basis of several reports into AI vulnerabilities that will be published next year. The organizers of the challenge say it sets a precedent for transparency around AI. But in this highly controlled environment, it is clear that it is only scratching the surface.
What took place at the annual DEF CON hacking conference provides something of a model for testing OpenAI’s ChatGPT and other sophisticated chatbots. Though with such enthusiastic backing from the companies themselves, I wonder how rigorous the supposed “hacks” actually are, or if, as has been a criticism in the past, the leading firms are merely paying lip service to accountability.
To be sure, nothing discovered at the convention is likely to keep OpenAI CEO Sam Altman awake at night. While one of the event’s organizers, SeedAI CEO Austin Carson, said he was prepared to bet me US$1,000 that there would be a “mind-blowing” vulnerability uncovered during the contest, it was highly unlikely to be anything that could not be fixed with a few adjustments by the AI company affected. The resulting research papers, due to be published in February, will be reviewed by the AI giants before publication — a chance to “duke it out” with the researchers, Carson said.
Those backing the event admit that the main focus of the contest is less about finding serious vulnerabilities and more about keeping up the discussion with the public and policymakers, continually highlighting the ways in which chatbots cannot be trusted. It is a worthwhile goal. Keen to not let the mistakes of social media be repeated, it is encouraging to see the government appreciate the value of the hacking community.
There is no better place to host this kind of contest than at DEF CON. Its anarchic roots stem from a long-running policy that you do not have to give your name to gain entry. That means the conference is able to attract the best and most notorious in the cybersecurity community, including people who might have a less-than-legal hacking past. For this reason, the event has an unprecedented record of publicizing startling cybersecurity discoveries and disclosures that have left major companies terrified — but ultimately made many of the technologies we all use every day much safer.
While the phrase “hack” evokes thoughts of malicious acts, the primary motivation of participants at the event is to share what vulnerabilities they have found in order to have them fixed.
“It’s the good guys being dangerous so that we know what the risks are,” says Kellee Wicker of the Wilson Center, a Washington-based think tank that has helped put the AI contest together and will be presenting the findings to policymakers. “If there’s a door with a broken lock, wouldn’t you rather the security guard find it than the thief?”
The companies could of course be more open with their technology but it is complex. The true nuts and bolts of how language learning models work is still under lock and key, and — as I have written previously — specifics around the training data used are increasingly being kept secret.
“It’s a frustrating dynamic,” said Rumman Chowdhury, former ethics lead at Twitter and now co-founder of nonprofit Humane Intelligence, another of the contest’s organizers. Fuller transparency is difficult for companies trying to protect intellectual property, trade secrets and personal data, she said.
But this is a healthy start. At her laptop, Hayes has not managed to make the chatbot share credit-card information. “Oh, this one’s good,” she says of the bot, as it foils a technique that had been successful in the past. Within chatbots, and broader AI, there are an uncountable number of quirks and exploits still waiting to be found. We should be grateful to the people taking the time to look for them.
Dave Lee is Bloomberg Opinion’s US technology columnist. Previously, he was a San Francisco-based correspondent at the Financial Times and BBC News.
This column does not necessarily reflect the opinion of the editorial board or Bloomberg LP and its owners.
From May 31 to June 2, 37 ministers of defense attended the 21st International Institute for Strategic Studies Shangri-La Dialogue in Singapore, including Chinese Minister of National Defense Dong Jun (董軍). Anyone who tried to separate Taiwan from China would be “crushed to pieces,” he said during the premier defense summit. In response to the threat, US Indo-Pacific Commander Admiral Samuel Paparo revealed the US military’s “Hellscape” strategy, with the aim of thwarting a potential Chinese invasion of Taiwan. The strategy involves turning the Taiwan Strait into an “unmanned hellscape” before Chinese forces can cross it, Paparo said in an
Since Nvidia Corp chief executive officer Jensen Huang’s (黃仁勳) arrival in Taiwan on May 26, he has dominated headlines across multiple local news outlets. Rather than speaking English, he has been seen several times conversing with locals in Hoklo (commonly known as Taiwanese), a local language no longer commonly used by the public. Due to his growing popularity and use of Hoklo, issues surrounding the preservation of native languages have resurfaced. Contrary to the stigmatizing belief that Hoklo is merely a language spoken by the uneducated, Huang’s actions have inspired many of his fans to revive their respective mother tongues. Unfortunately, even
Preserving its global dominance appears to have driven the West’s expanding involvement in the Ukraine conflict, with former British prime minister Boris Johnson recently arguing in a column that a Russian victory would be “a turning point in history, the moment when the West finally loses its post-war hegemony.” Such a decisive outcome, however, seems doubtful, given the attritional character of the Ukraine war and the progressively escalating Western involvement in the conflict. The defining moment that formally brings the era of Western preeminence to an end is more likely to be a surprise Chinese aggression aimed at subjugating Taiwan. With the
The pro-China camp in Taiwan is apparently displeased with Nvidia Corp founder and CEO Jensen Huang (黃仁勳), and an Internet celebrity even searched for and disclosed his personal information online. Such disapproval was not only due to Huang using the word “country” to describe Taiwan or his praise for the nation’s technology industry, but also because his very existence implies support for Taiwan. After reforms in the Tang (唐) and Song (宋) dynasties, the class system of the “four occupations” — academic, farmer, worker and businessperson — took shape in China. Prior to the changes, businesspeople held influential roles in China. The