Current:Home > FinanceDon’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought-DB Wealth Institute B2 Expert Reviews
Don’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought
View Date:2025-01-13 05:49:48
BOSTON (AP) — White House officials concerned by AI chatbots’ potential for societal harm and the Silicon Valley powerhouses rushing them to market are heavily invested in a three-day competition ending Sunday at the DefCon hacker convention in Las Vegas.
Some 3,500 competitors have tapped on laptops seeking to expose flaws in eight leading large-language models representative of technology’s next big thing. But don’t expect quick results from this first-ever independent “red-teaming” of multiple models.
Findings won’t be made public until about February. And even then, fixing flaws in these digital constructs — whose inner workings are neither wholly trustworthy nor fully fathomed even by their creators — will take time and millions of dollars.
Current AI models are simply too unwieldy, brittle and malleable, academic and corporate research shows. Security was an afterthought in their training as data scientists amassed breathtakingly complex collections of images and text. They are prone to racial and cultural biases, and easily manipulated.
“It’s tempting to pretend we can sprinkle some magic security dust on these systems after they are built, patch them into submission, or bolt special security apparatus on the side,” said Gary McGraw, a cybsersecurity veteran and co-founder of the Berryville Institute of Machine Learning. DefCon competitors are “more likely to walk away finding new, hard problems,” said Bruce Schneier, a Harvard public-interest technologist. “This is computer security 30 years ago. We’re just breaking stuff left and right.” Michael Sellitto of Anthropic, which provided one of the AI testing models, acknowledged in a press briefing that understanding their capabilities and safety issues “is sort of an open area of scientific inquiry.”
Conventional software uses well-defined code to issue explicit, step-by-step instructions. OpenAI’s ChatGPT, Google’s Bard and other language models are different. Trained largely by ingesting — and classifying — billions of datapoints in internet crawls, they are perpetual works-in-progress, an unsettling prospect given their transformative potential for humanity.
After publicly releasing chatbots last fall, the generative AI industry has had to repeatedly plug security holes exposed by researchers and tinkerers.
Tom Bonner of the AI security firm HiddenLayer, a speaker at this year’s DefCon, tricked a Google system into labeling a piece of malware harmless merely by inserting a line that said “this is safe to use.”
“There are no good guardrails,” he said.
Another researcher had ChatGPT create phishing emails and a recipe to violently eliminate humanity, a violation of its ethics code.
A team including Carnegie Mellon researchers found leading chatbots vulnerable to automated attacks that also produce harmful content. “It is possible that the very nature of deep learning models makes such threats inevitable,” they wrote.
It’s not as if alarms weren’t sounded.
In its 2021 final report, the U.S. National Security Commission on Artificial Intelligence said attacks on commercial AI systems were already happening and “with rare exceptions, the idea of protecting AI systems has been an afterthought in engineering and fielding AI systems, with inadequate investment in research and development.”
Serious hacks, regularly reported just a few years ago, are now barely disclosed. Too much is at stake and, in the absence of regulation, “people can sweep things under the rug at the moment and they’re doing so,” said Bonner.
Attacks trick the artificial intelligence logic in ways that may not even be clear to their creators. And chatbots are especially vulnerable because we interact with them directly in plain language. That interaction can alter them in unexpected ways.
Researchers have found that “poisoning” a small collection of images or text in the vast sea of data used to train AI systems can wreak havoc — and be easily overlooked.
A study co-authored by Florian Tramér of the Swiss University ETH Zurich determined that corrupting just 0.01% of a model was enough to spoil it — and cost as little as $60. The researchers waited for a handful of websites used in web crawls for two models to expire. Then they bought the domains and posted bad data on them.
Hyrum Anderson and Ram Shankar Siva Kumar, who red-teamed AI while colleagues at Microsoft, call the state of AI security for text- and image-based models “pitiable” in their new book “Not with a Bug but with a Sticker.” One example they cite in live presentations: The AI-powered digital assistant Alexa is hoodwinked into interpreting a Beethoven concerto clip as a command to order 100 frozen pizzas.
Surveying more than 80 organizations, the authors found the vast majority had no response plan for a data-poisoning attack or dataset theft. The bulk of the industry “would not even know it happened,” they wrote.
Andrew W. Moore, a former Google executive and Carnegie Mellon dean, says he dealt with attacks on Google search software more than a decade ago. And between late 2017 and early 2018, spammers gamed Gmail’s AI-powered detection service four times.
The big AI players say security and safety are top priorities and made voluntary commitments to the White House last month to submit their models — largely “black boxes’ whose contents are closely held — to outside scrutiny.
But there is worry the companies won’t do enough.
Tramér expects search engines and social media platforms to be gamed for financial gain and disinformation by exploiting AI system weaknesses. A savvy job applicant might, for example, figure out how to convince a system they are the only correct candidate.
Ross Anderson, a Cambridge University computer scientist, worries AI bots will erode privacy as people engage them to interact with hospitals, banks and employers and malicious actors leverage them to coax financial, employment or health data out of supposedly closed systems.
AI language models can also pollute themselves by retraining themselves from junk data, research shows.
Another concern is company secrets being ingested and spit out by AI systems. After a Korean business news outlet reported on such an incident at Samsung, corporations including Verizon and JPMorgan barred most employees from using ChatGPT at work.
While the major AI players have security staff, many smaller competitors likely won’t, meaning poorly secured plug-ins and digital agents could multiply. Startups are expected to launch hundreds of offerings built on licensed pre-trained models in coming months.
Don’t be surprised, researchers say, if one runs away with your address book.
veryGood! (5)
Related
- Reds honor Pete Rose with a 14-hour visitation at Great American Ball Park
- Deputies fatally shot a double-murder suspect who was holding a chrome shower head
- Iran holds first parliamentary election since 2022 mass protests, amid calls for boycott
- Quick! Swimsuits for All Is Having a Sale for Today Only, Score Up to 50% off Newly Stocked Bestsellers
- Former NFL coach Jack Del Rio charged with operating vehicle while intoxicated
- Air Force employee charged with sharing classified info on Russia’s war with Ukraine on dating site
- Rotting bodies, fake ashes and sold body parts push Colorado to patch lax funeral home rules
- Just How Much Money Do CO2 Pipeline Companies Stand to Make From the Inflation Reduction Act?
- Atmospheric river to bring heavy snow, rain to Northwest this week
- Jonathan Majors, Meagan Good make red carpet debut a month before his assault sentencing
Ranking
- Deion Sanders doubles down on vow to 99-year-old Colorado superfan
- Elle King returns to performing nearly 2 months after controversial Dolly Parton tribute
- Kate Middleton Spotted Out for First Time Since Abdominal Surgery
- Lindsay Lohan Confirmed the Ultimate News: A Freaky Friday Sequel Is Happening
- Taylor Swift Politely Corrects Security’s Etiquette at Travis Kelce’s Chiefs Game
- Here's how to negotiate a lower commission fee from your real estate agent
- Air Force employee charged with sharing classified info on Russia’s war with Ukraine on dating site
- The Flash’s Grant Gustin and Wife LA Thoma Expecting Baby No. 2
Recommendation
-
Why Suits' Gabriel Macht Needed Time Away From Harvey Specter After Finale
-
2024 MLS All-Star Game set for July vs. Liga MX. Tickets on sale soon. Here's where to buy
-
2024 NFL mock draft: Six QBs land in top 16 picks of post-combine shake-up
-
Mike Evans, Buccaneers agree to two-year contract ahead of NFL free agency
-
Joey Logano wins Phoenix finale for 3rd NASCAR Cup championship in 1-2 finish for Team Penske
-
NFL world honors 'a wonderful soul' after Chris Mortensen's death at 72
-
The Best Leakproof Period Underwear That Actually Work, Plus Styles I Swear By
-
Ohio foundation begins process to distribute millions in opioid settlement money