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.
Deterrence is fading; war is looming on the Taiwan Strait and for other targets of the China-enabled dictatorship alliance, and after three years the cure is just dawning on the Biden Administration. Now mind you, for a May 28, 2024 interview with Time magazine, President Joe Biden made his 5th public commitment that the United States would defend Taiwan. Less than three weeks later the United States Navy, along with ships from navies of Japan, Canada, the Netherlands, and France, were conducting the Valiant Shield joint force exercise in the Philippine Sea south of Taiwan and in the South China Sea to
The official media of the Chinese Communist Party (CCP) reacted to the May 20 inauguration speech of President William Lai (賴清德) by asserting: “Lai’s words reveal his true intention of sacrificing peace and stability across the Taiwan Strait for his own desire for power.” This baseless accusation by Beijing that Lai is manipulating Taiwanese to resist unification with China for his personal gain, is part of a broader CCP information warfare campaign that has intensified since Lai’s election. This campaign, orchestrated by the United Front Work Department, the CCP’s agency for coordinating influence operations and propaganda, aims to demoralize Taiwanese,
A facile way to frame the future of US foreign policy is to set up two scenarios as a binary choice. If former US president Donald Trump returns to the White House, the US becomes isolationist. If US President Joe Biden wins re-election, the US remains broadly internationalist. That framing neglects a change that might be less obvious but more consequential for other countries, a shift that would keep playing out no matter who wins in November: For the first time in its two-and-a-half centuries, the US would stop looking at the world through the lens of its own exceptionalism, and
Minister of Health and Welfare Chiu Tai-yuan (邱泰源) on Friday said the ministry supports keeping priority seats on public transportation, but is considering expanding the eligibility criteria and renaming the seats. Chiu’s remarks came after local news media over the past few weeks reported incidents involving priority seats, once again sparking heated discussion about whether the seats should be abolished or regulations regarding them should be revised. On June 11, an older woman asked a young woman on a Taipei MRT train to yield her priority seat. The young woman refused, saying that she needed the seat after working a 12-hour shift.