Machine-learning boffins 'summon demons' in AI to find exploitable bugs

There's a low awareness of vulnerabilities in neural networks, say researchers


Surrounded by all the hype in AI, it’s easy to sing the praises of machine learning without realizing that systems can be easily exploited.

As governments, businesses, and hospitals are beginning to explore the use of machine learning for data analysis and decision making, it’s important to bolster security.

In a paper [PDF] ominously titled “Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning,” a group of researchers from the University of Maryland are trying to find bugs by causing “silent failures.”

Machine learning systems have often been compared to black boxes. They are trained to map input data to output data by learning from an algorithm. But what happens in-between? It is tricky to decipher how the machine arrives at its final answer, and the lack of transparency means that breaches can pass through silently.

Inputs can be corrupted in a way to manipulate the outputs. “Like all software, ML [machine learning] algorithm implementations have bugs, and some of these bugs could affect learning tasks. Thus, attacks can construct malicious inputs to ML algorithm implementations that exploit these bugs,” the paper said.

This could be a huge problem in the future, Tudor Dumitraș, coauthor of the paper and assistant professor at the University of Maryland, told The Register.

People could fiddle with cost function algorithms to crank up the price of insurance bonuses, or criminals could evade facial recognition on CCTV cameras, assuming they know the program’s source code and can control input. It’s a realistic possibility, granted that a lot of machine learning software is open source.

“Once you start looking for bugs, you find more and more of them. And we didn’t have to look very hard. The community [of software developers] isn’t really aware of this problem – it doesn’t seem to be a high priority,” noted Dumitraș.

The team used a semi-automated technique called “steered fuzzing” to comb through machine learning programs for bugs. Failures such as mispredictions, or false outcomes, lead to detectable crashes in the program.

First, a test case is used to mutate the inputs and corrupt the system. Using OpenCV, an open source computer vision and machine learning software library, an example would be to start with an image that contains a human face. Steered fuzzing should mutate the image and compromise the output by making the face undetectable.

Next, the American Fuzzy Lop, a software testing technique, is applied to make the dodgy inputs crash the system and to find where the system was manipulated.

Looking at three programs: OpenCV; Malheur, a library for analyzing and clustering malware behavior; and scikit-learn, a catalog of data analysis tools, researchers found seven exploitable bugs. Three of the vulnerabilities were filed under new additions in the Common Vulnerabilities and Exposures (CVE) dictionary.

After disclosing the results, some of the more subtle bugs were not granted CVE numbers and were labelled “WONTFIX” – a result that shows that ML bugs are currently a misunderstood threat.

“It’s our first attempt at this kind of project. ML is a relatively new area. Although people are working on finding bugs, no one has done a systematic treatment of machine learning implementations yet,” Dumitraș told The Register. ®

Broader topics


Other stories you might like

  • Demand for PC and smartphone chips drops 'like a rock' says CEO of China’s top chipmaker
    Markets outside China are doing better, but at home vendors have huge component stockpiles

    Demand for chips needed to make smartphones and PCs has dropped "like a rock" – but mostly in China, according to Zhao Haijun, the CEO of China's largest chipmaker Semiconductor Manufacturing International Corporation (SMIC).

    Speaking on the company's Q1 2022 earnings call last Friday, Zhao said smartphone makers currently have five months inventory to hand, so are working through that stockpile before ordering new product. Sales of PCs, consumer electronics and appliances are also in trouble, the CEO said, leaving some markets oversupplied with product for now. But unmet demand remains for silicon used for Wi-Fi 6, power conversion, green energy products, and analog-to-digital conversion.

    Zhao partly attributed sales slumps to the Ukraine war which has made the Russian market off limits to many vendors and effectively taken Ukraine's 44 million citizens out of the global market for non-essential purchases.

    Continue reading
  • Colocation consolidation: Analysts look at what's driving the feeding frenzy
    Sometimes a half-sized shipping container at the base of a cell tower is all you need

    Analysis Colocation facilities aren't just a place to drop a couple of servers anymore. Many are quickly becoming full-fledged infrastructure-as-a-service providers as they embrace new consumption-based models and place a stronger emphasis on networking and edge connectivity.

    But supporting the growing menagerie of value-added services takes a substantial footprint and an even larger customer base, a dynamic that's driven a wave of consolidation throughout the industry, analysts from Forrester Research and Gartner told The Register.

    "You can only provide those value-added services if you're big enough," Forrester research director Glenn O'Donnell said.

    Continue reading
  • D-Wave deploys first US-based Advantage quantum system
    For those that want to keep their data in the homeland

    Quantum computing outfit D-Wave Systems has announced availability of an Advantage quantum computer accessible via the cloud but physically located in the US, a key move for selling quantum services to American customers.

    D-Wave reported that the newly deployed system is the first of its Advantage line of quantum computers available via its Leap quantum cloud service that is physically located in the US, rather than operating out of D-Wave’s facilities in British Columbia.

    The new system is based at the University of Southern California, as part of the USC-Lockheed Martin Quantum Computing Center hosted at USC’s Information Sciences Institute, a factor that may encourage US organizations interested in evaluating quantum computing that are likely to want the assurance of accessing facilities based in the same country.

    Continue reading
  • Bosses using AI to hire candidates risk discriminating against disabled applicants
    US publishes technical guide to help organizations avoid violating Americans with Disabilities Act

    The Biden administration and Department of Justice have warned employers using AI software for recruitment purposes to take extra steps to support disabled job applicants or they risk violating the Americans with Disabilities Act (ADA).

    Under the ADA, employers must provide adequate accommodations to all qualified disabled job seekers so they can fairly take part in the application process. But the increasing rollout of machine learning algorithms by companies in their hiring processes opens new possibilities that can disadvantage candidates with disabilities. 

    The Equal Employment Opportunity Commission (EEOC) and the DoJ published a new document this week, providing technical guidance to ensure companies don't violate ADA when using AI technology for recruitment purposes.

    Continue reading
  • How ICE became a $2.8b domestic surveillance agency
    Your US tax dollars at work

    The US Immigration and Customs Enforcement (ICE) agency has spent about $2.8 billion over the past 14 years on a massive surveillance "dragnet" that uses big data and facial-recognition technology to secretly spy on most Americans, according to a report from Georgetown Law's Center on Privacy and Technology.

    The research took two years and included "hundreds" of Freedom of Information Act requests, along with reviews of ICE's contracting and procurement records. It details how ICE surveillance spending jumped from about $71 million annually in 2008 to about $388 million per year as of 2021. The network it has purchased with this $2.8 billion means that "ICE now operates as a domestic surveillance agency" and its methods cross "legal and ethical lines," the report concludes.

    ICE did not respond to The Register's request for comment.

    Continue reading
  • Fully automated AI networks less than 5 years away, reckons Juniper CEO
    You robot kids, get off my LAN

    AI will completely automate the network within five years, Juniper CEO Rami Rahim boasted during the company’s Global Summit this week.

    “I truly believe that just as there is this need today for a self-driving automobile, the future is around a self-driving network where humans literally have to do nothing,” he said. “It's probably weird for people to hear the CEO of a networking company say that… but that's exactly what we should be wishing for.”

    Rahim believes AI-driven automation is the latest phase in computer networking’s evolution, which began with the rise of TCP/IP and the internet, was accelerated by faster and more efficient silicon, and then made manageable by advances in software.

    Continue reading
  • Pictured: Sagittarius A*, the supermassive black hole at the center of the Milky Way
    We speak to scientists involved in historic first snap – and no, this isn't the M87*

    Astronomers have captured a clear image of the gigantic supermassive black hole at the center of our galaxy for the first time.

    Sagittarius A*, or Sgr A* for short, is 27,000 light-years from Earth. Scientists knew for a while there was a mysterious object in the constellation of Sagittarius emitting strong radio waves, though it wasn't really discovered until the 1970s. Although astronomers managed to characterize some of the object's properties, experts weren't quite sure what exactly they were looking at.

    Years later, in 2020, the Nobel Prize in physics was awarded to a pair of scientists, who mathematically proved the object must be a supermassive black hole. Now, their work has been experimentally verified in the form of the first-ever snap of Sgr A*, captured by more than 300 researchers working across 80 institutions in the Event Horizon Telescope Collaboration. 

    Continue reading
  • Shopping for malware: $260 gets you a password stealer. $90 for a crypto-miner...
    We take a look at low, low subscription prices – not that we want to give anyone any ideas

    A Tor-hidden website dubbed the Eternity Project is offering a toolkit of malware, including ransomware, worms, and – coming soon – distributed denial-of-service programs, at low prices.

    According to researchers at cyber-intelligence outfit Cyble, the Eternity site's operators also have a channel on Telegram, where they provide videos detailing features and functions of the Windows malware. Once bought, it's up to the buyer how victims' computers are infected; we'll leave that to your imagination.

    The Telegram channel has about 500 subscribers, Team Cyble documented this week. Once someone decides to purchase of one or more of Eternity's malware components, they have the option to customize the final binary executable for whatever crimes they want to commit.

    Continue reading

Biting the hand that feeds IT © 1998–2022