For the past decade, artificial intelligence (AI) has been used to recognize faces, rate creditworthiness and predict the weather. At the same time, increasingly sophisticated hacks using stealthier methods have escalated. The combination of AI and cybersecurity was inevitable as both fields sought better tools and new uses for their technology. However, there is a massive problem that threatens to undermine these efforts and could allow adversaries to bypass digital defenses undetected.
The danger is data poisoning: manipulating the information used to train machines offers a virtually untraceable method to circumvent AI-powered defenses. Many companies might not be ready to deal with escalating challenges.
The global market for AI cybersecurity is already expected to triple by 2028 to US$35 billion. Security providers and their clients might have to patch together multiple strategies to keep threats at bay.
Illustration: Louise Ting
The very nature of machine learning, a subset of AI, is the target of data poisoning.
Given reams of data, computers can be trained to categorize information correctly. A system might not have seen a picture of Lassie, but given enough examples of different animals that are correctly labeled by species (and even breed) it should be able to surmise she is a dog. With even more samples, it would be able to correctly guess the breed of the famous TV canine: rough collie.
The computer does not really know. It is merely making statistically informed inference based on past training data.
That same approach is used in cybersecurity. To catch malicious software, companies feed their systems with data and let the machine learn by itself. Computers armed with numerous examples of both good and bad code can learn to look out for malicious software (or even snippets of software) and catch it.
An advanced technique called neural networks — which mimics the structure and processes of the human brain — runs through training data and makes adjustments based on both known and new information.
Such a network need not have seen a specific piece of malevolent code to surmise that it is bad. It has learned for itself and can adequately predict good versus evil.
All of that is powerful, but it is not invincible.
Machine-learning systems require a huge number of correctly labeled samples to start getting good at prediction. Even the largest cybersecurity companies are able to collate and categorize only a limited number of examples of malware, so they have little choice but to supplement their training data. Some of the data can be crowd-sourced.
“We already know that a resourceful hacker can leverage this observation to their advantage,” Giorgio Severi, a doctoral student at Northwestern University, said in a recent presentation at the USENIX Security Symposium.
Using the animal analogy, if feline-phobic hackers wanted to cause havoc, they could label a bunch of photos of sloths as cats, and feed the images into an open-source database of house pets. Since the tree-hugging mammals would appear far less often in a corpus of domesticated animals, this small sample of poisoned data has a good chance of tricking a system into spitting out sloth pics when asked to show kittens.
It is the same technique for more malicious hackers.
By carefully crafting malicious code, labeling these samples as good, and then adding it to a larger batch of data, a hacker can trick a neutral network into surmising that a snippet of software that resembles the bad example is, in fact, harmless.
Catching the miscreant samples is almost impossible. It is far harder for a human to rummage through computer code than to sort pictures of sloths from those of cats.
In a presentation at the Hacks In Taiwan security conference in Taipei last year, researchers Cheng Shin-ming (鄭欣明) and Tseng Ming-huei (曾明慧) showed that backdoor code could fully bypass defenses by poisoning less than 0.7 percent of the data submitted to the machine-learning system.
Not only does it mean that only a few malicious samples are needed, but it indicates that a machine-learning system can be rendered vulnerable even if it uses only a small amount of unverified open-source data.
The industry is not blind to the problem, and this weakness is forcing cybersecurity companies to take a much broader approach to bolstering defenses.
One way to help prevent data poisoning is for scientists who develop AI models to regularly check that all the labels in their training data are accurate.
OpenAI, a research company cofounded by Elon Musk, said that when its researchers curated their data sets for a new image-generating tool, they would regularly pass the data through special filters to ensure the accuracy of each label.
That “removes the large majority of images which are falsely labeled,” a spokeswoman said.
To stay safe, companies need to ensure their data is clean, but that means training their systems with fewer examples than they would get with open source offerings.
In machine learning, sample size matters.
This cat-and-mouse game between attackers and defenders has been going on for decades, with AI simply the latest tool deployed to help the good side stay ahead.
Remember: Artificial intelligence is not omnipotent. Hackers are always looking for their next exploit.
Tim Culpan is a technology columnist for Bloomberg Opinion. Based in Taipei, he writes about Asian and global businesses and trends. He previously covered the beat at Bloomberg News.
US President Donald Trump and Chinese President Xi Jinping (習近平) were born under the sign of Gemini. Geminis are known for their intelligence, creativity, adaptability and flexibility. It is unlikely, then, that the trade conflict between the US and China would escalate into a catastrophic collision. It is more probable that both sides would seek a way to de-escalate, paving the way for a Trump-Xi summit that allows the global economy some breathing room. Practically speaking, China and the US have vulnerabilities, and a prolonged trade war would be damaging for both. In the US, the electoral system means that public opinion
In their recent op-ed “Trump Should Rein In Taiwan” in Foreign Policy magazine, Christopher Chivvis and Stephen Wertheim argued that the US should pressure President William Lai (賴清德) to “tone it down” to de-escalate tensions in the Taiwan Strait — as if Taiwan’s words are more of a threat to peace than Beijing’s actions. It is an old argument dressed up in new concern: that Washington must rein in Taipei to avoid war. However, this narrative gets it backward. Taiwan is not the problem; China is. Calls for a so-called “grand bargain” with Beijing — where the US pressures Taiwan into concessions
The term “assassin’s mace” originates from Chinese folklore, describing a concealed weapon used by a weaker hero to defeat a stronger adversary with an unexpected strike. In more general military parlance, the concept refers to an asymmetric capability that targets a critical vulnerability of an adversary. China has found its modern equivalent of the assassin’s mace with its high-altitude electromagnetic pulse (HEMP) weapons, which are nuclear warheads detonated at a high altitude, emitting intense electromagnetic radiation capable of disabling and destroying electronics. An assassin’s mace weapon possesses two essential characteristics: strategic surprise and the ability to neutralize a core dependency.
Chinese President and Chinese Communist Party (CCP) Chairman Xi Jinping (習近平) said in a politburo speech late last month that his party must protect the “bottom line” to prevent systemic threats. The tone of his address was grave, revealing deep anxieties about China’s current state of affairs. Essentially, what he worries most about is systemic threats to China’s normal development as a country. The US-China trade war has turned white hot: China’s export orders have plummeted, Chinese firms and enterprises are shutting up shop, and local debt risks are mounting daily, causing China’s economy to flag externally and hemorrhage internally. China’s
RSS