Pig butchering scammers turned high tech | Chinese authorities detained four Taiwanese Foxconn employees | TikTok cuts jobs as content moderator shift to AI

Good morning. It's Monday 14th October.

The Daily Cyber & Tech Digest focuses on the topics we work on, including cybersecurity, critical technologies, foreign interference & disinformation.

Follow us on Twitter and on LinkedIn.

• Pig butchering scammers are increasingly turning to AI, deepfakes, and dangerous malware in a way that makes their pig butchering operations even more convincing. WIRED

• Chinese authorities have detained four Taiwanese employees of Foxconn, a major Apple supplier, accusing them of a breach of trust. The New York Times

• Social media platform TikTok is laying off hundreds of employees from its global workforce as it shifts towards AI content moderation. Reuters

ASPI

Acquiring trust, not sovereign datasets, is the key to effective AI regulation
The Strategist
Jocelinn Kang and Karly Winkler
Building public trust is vital to creating effective artificial intelligence regulation in Australia—not sovereign large-scale datasets. The assertion that AI regulation would be ineffective without the existence of large-scale sovereign datasets​​​​ is flawed. Public trust in AI systems is low in Australia. Only 34 percent of Australians are willing to trust AI systems, according to research by the University of Queensland and KPMG. For AI to flourish, Australians need confidence that their data will be safe in the hands of those who will use it to build and improve AI systems, and that these systems will be deployed safely, securely and responsibly.

The CCP's digital charm offensive: How TikTok's search algorithm and pro-China influence networks indoctrinate Gen Z users in the United States
Network Contagion Research Institute
Joel Finkelstein, et. al.
As ASPI details, the CCP weaponizes prima facia benign travel vloggers to manage perceptions of China abroad, particularly as relates to restive border areas like Tibet, Xinjiang, and Inner Mongolia. As the report remarks, one tactic employed by these frontier influencers is ensuring “that state-backed content ranks well in search results because search-engine algorithms tend to prioritize fresh content and channels that post regularly.” As will be discussed below, our user journey findings directly confirm ASPI’s 2021 findings.

The World

Pig butchering scams are going high tech
WIRED
Many digital scams have traditionally relied on social engineering, or tricking victims into giving away their money willingly, rather than leaning on malware or other highly technical methods. But researchers have increasingly sounded the alarm that scammers are incorporating generative AI content and deepfakes to expand the scale and effectiveness of their operations. Around 200,000 people, from at least 60 countries, have been trafficked to compounds largely in Myanmar, Cambodia, and Laos over the last five years. However, as WIRED reporting has shown, these operations are spreading globally—with scamming infrastructure emerging in the Middle East, Eastern Europe, Latin America, and West Africa.

Australia

Half of Australia’s law enforcement agencies have banned officers using encrypted messaging apps
The Guardian
Josh Taylor
Half of the Australian law enforcement agencies across Australia have banned their officers from using messaging apps like WhatsApp and Signal, after New South Wales police last week banned the practice. Last week, the NSW police force said it had introduced security software that meant “social media and other personal apps will not work or be downloadable” on NSW police force issued devices. It was reported that about 17,000 officers had been ordered to remove communications apps from their devices.

ASIO chief Mike Burgess tells social media summit of 'disturbing resurgence' in youth terror cases
ABC News
Daniel Keane
At a summit examining the harmful effects of online platforms on young people, Mike Burgess spoke in broad terms about the ways in which social media and digital technologies were fuelling threats to national security. Burgess was emphatic that the problem was an especially pressing one for policymakers focused on education and child safety, pointing out that "all" of the nation's most recent terror cases "were allegedly perpetrated by young people", including one as young as 14.

Technology allows organised crime to carry out hits, distribute drugs from a distance
ABC News
David Estcourt
A series of raids conducted by the Australian Federal Police last month saw dozens of people charged with illicit drug trafficking, conspiracy, destruction of records and supporting a criminal organisation and firearm charges. The key to these charges was the AFP penetrating the so-called "Ghost" platform, which gave them access to 125,000 messages sent by users. A law enforcement officer says they have seen crews become younger, more violent and more reckless.

Satellite communications are vulnerable, but good alternatives are available
The Strategist
Alan Seymour
What happens if space, crucial for Australian Defence Force missions, becomes inaccessible during a major conflict? If satellite communications and support are disabled or destroyed, existing critical communications networks will be lost. The data flow that fills the ADF’s common operating picture would dwindle to intermittent trickles. There are alternatives. The main one pre-dates satellites, high-frequency radio.

China

Taiwanese employees of Apple supplier detained in China
The New York Times
Keith Bradsher and Amy Chang Chien
Chinese authorities have detained four employees of Foxconn, the Taiwanese manufacturer that makes Apple iPhones, Taiwan said, in the latest incident involving government scrutiny of the private sector in mainland China. The police in Zhengzhou, China, had accused each of the four Taiwanese workers of an offense comparable to Taiwan’s “crime of breach of trust,” according to a statement on Thursday from Taiwan’s Mainland Affairs Council. Taiwan’s government said that they had been accused of a breach of trust, but that their employer, Foxconn, had denied the company suffered any losses.

• China detains employees at Apple iPhone factory run by Foxconn
  The Wall Street Journal
  Joyu Wang
  The employees worked at a complex run by Taiwan’s Foxconn Technology Group in Zhengzhou, China, said Taiwanese agencies responsible for managing relations with China. The Zhengzhou facility plays a central role in Apple’s iPhone supply chain and has sometimes been called iPhone City. Taiwan’s Mainland Affairs Council, which handles policy toward Beijing, quoted Foxconn as saying that the company didn’t suffer any financial loss connected to the actions of the employees. The council in June upgraded its alert level for travel to China to the second-highest level, saying Taiwanese people should avoid nonessential trips. It said Beijing’s tightened national-security laws have led to Taiwanese citizens being illegally detained or interrogated.

Websites blocked in Hong Kong – when, how, and why the list is growing
Hong Kong Free Press
A growing list of websites – including those related to the US military, Taiwan, local politics and, now, a media platform – have been blocked in Hong Kong. A key feature of Hong Kong’s business environment that differentiates it from mainland China is its free and open internet. However, the city is not immune to internet controls, with a growing list of websites apparently blocked by telecoms firms and Internet Service Providers, with some citing police demands.

China races to outflank Elon Musk's Starlink satellite internet service
Nikkei Asia
Cissy Zhou
China aims to launch constellations of internet satellites, rivaling Elon Musk's Starlink. But experts warn that Beijing’s drive to establish itself in the sector holds the potential for China to export its restrictive model of online governance. China plans to launch as many as 3,900 satellites into low earth orbit by 2027, moving toward a larger ambition of having at least three mega constellations comprising over 10,000 satellites each. These are called GW; Qianfan, formerly known as G60; and Honghu.

US-blacklisted Chinese surveillance camera maker Hikvision said to be cutting jobs
South China Morning Post
Ann Cao
Chinese video surveillance technology supplier Hikvision is reportedly cutting jobs in its research and development department, as the US-sanctioned company grapples with business pressure under geopolitical and economic headwinds. The Hangzhou, Zhejiang-based company is expected to lay off over 1,000 employees in China in a significant downsizing of its R&D team, according to a report on Friday from local online news platform Sina Tech.

USA

Trump-aligned group believed to have been attacked by Chinese hackers
The Washington Post
Josh Dawsey, Isaac Arnsdorf and Perry Stein
A political organization helping prepare for the potential presidential transition of Donald Trump recently experienced a cyberattack by what federal authorities believe are Chinese hackers, according to people familiar with the matter. Materials were taken from online accounts belonging to the America First Policy Institute, which has put together policy proposals for a second Trump term and recommendations for jobs and agencies, according to the people, who spoke on the condition of anonymity to describe the investigation.

National Public Data files for bankruptcy, citing fallout from cyberattack
The Record by Recorded Future
Jonathan Greig
A background check giant that was hacked earlier this year has filed for bankruptcy, claiming in court documents that dozens of states have filed legal claims against it. National Public Data is one of the biggest background check companies, allowing its customers to search billions of records with instant results. In a case management summary submitted alongside the bankruptcy filing, the company said “a large portion” of their business “serves healthcare institutions” that “prohibit entry of individuals with background issues.” The company admitted in August that a late December 2023 data breach was the source of personal information that was sold on the dark web in April 2024 and again throughout the summer.

‘The younger the user, the better’: TikTok knew app posed mental health risks for children
The Age
TikTok’s political woes deepened after an inadvertent legal disclosure detailed how aware the app’s managers apparently were of its potential risks to children, airing explosive revelations as the Chinese-owned company tries to fend off a US ban. The popular video-sharing platform’s internal research showed that children were particularly susceptible to its powerful algorithmic feeds and that excessive use of the site could lead to mental health issues, according to a lawsuit filed by the state of Kentucky earlier this week.

Musk is going all in to elect Trump
The New York Times
Theodore Schleifer, Maggie Haberman, Ryan Mac and Jonathan Swan
In the final weeks of the presidential campaign, the richest man in the world has involved himself in the US election in a manner unparalleled in modern history. Elon Musk, seen over the weekend jumping for joy alongside former President Donald Trump at a rally in Butler, Pennsylvania, is now talking to the Republican candidate multiple times a week. He has relentlessly promoted Mr. Trump’s candidacy to his 201 million followers on X, and has used it to spread conspiracy theories about the Democratic Party and to insult its candidate, Vice President Kamala Harris.

Southeast Asia

ByteDance's TikTok cuts hundreds of jobs in shift towards AI content moderation
Reuters
Rozanna Latiff
Social media platform TikTok is laying off hundreds of employees from its global workforce, including a large number of staff in Malaysia, the company said on Friday, as it shifts focus towards a greater use of AI in content moderation. TikTok, owned by China's ByteDance, later clarified that less than 500 employees in Malaysia were affected. Several hundred employees were expected to be impacted globally as part of a wider plan to improve its moderation operations.

Temu enters Vietnam and Brunei as app faces ban in Indonesia
South China Morning Post
Coco Feng
International discount-shopping platform Temu, operated by Pinduoduo owner PDD Holdings, is expanding into Vietnam and Brunei to boost its Southeast Asia operations, following Indonesia’s recent move to ban the popular e-commerce app. Temu’s website in Vietnam, however, showed that the company’s foray into one of the fastest-growing economies in the region was apparently rushed. It currently supports only English as well as transactions made via credit card and Google Pay, while excluding leading Vietnamese mobile payment service Momo.

South & Central Asia

What are digital arrests, the newest deepfake tool used by cybercriminals?
Al Jazeera
Dwayne Oxford
An Indian textile baron has revealed that he was duped out of 70 million rupees or US$833,000 by online scammers impersonating federal investigators and even the Supreme Court chief justice. The fraudsters posing as officers from India’s Central Bureau of Investigation called SP Oswal, chairman and managing director of the textile manufacturer Vardhman, on August 28 and accused him of money laundering. He was ordered to keep Skype open on his phone 24/7 during which he was interrogated and threatened with arrest.

Ukraine-Russia

Russia’s illicit Starlink terminals help power its advance in Ukraine
The Washington Post
Alex Horton, Serhii Korolchuk and Eva Dou
Russian forces have become deadlier and more agile with the help of illicit Starlink terminals, allowing them to use satellite internet to enhance coordination during assaults, fly more drone sorties and batter Ukrainian troops with accurate artillery fire despite US efforts to stop the flow of technology. The terminals, which give commanders live battlefield views with drones and secure communication between soldiers, are subject to prohibitions that outlaw many US electronics from reaching Moscow. Yet there is a burgeoning black market of Starlinks bringing the terminals to Russians on the front, and their proliferation has been an important factor in Russia’s recent gains during its offensive.

Ukraine police arrest hacker for operating illegal VPN service to access sanctioned Russian sites
The Record by Recorded Future
Daryna Antoniuk
Ukrainian law enforcement has arrested a local hacker who allegedly operated a large virtual private network service allowing users to access Russian websites sanctioned in Ukraine. The 28-year-old man is accused of setting up a VPN server room in his apartment in the western Ukrainian city of Khmelnytskyi. He also rented servers located in Germany, France, the Netherlands and Russia, “giving the enemy's special services access to information about all users of the VPN,” Ukrainian cyber police said in a statement.

Europe

Pro-Russia hackers target Flemish parliament, Belgian media ahead of local elections
POLITICO
Ketrin Jochecová
The pro-Russia hacker group NoName057 carried out cyberattacks on Friday against the Flemish parliament website and several Belgian media outlets, including Belga News and De Standaard. "We continue to send DDoS greetings to Belgium," said the pro-Russian collective on Telegram. Distributed denial-of-service attacks aim to overwhelm servers with requests, rendering the websites unaccessible for some time.

France’s first all-digital, cyber-secure multi-role frigate kicks off sea trials
Defense Post
Christine Casimiro
The first French Defense and Intervention Frigate, built by Naval Group, has officially begun its sea trials from the firm’s Lorient shipyard. The vessels are designed and produced using the latest digital technology, making them the first frigates with a digital architecture that allows for quick adaptability to current and future threats. The lead ship, named Amiral Ronarc’h (D660), is the first out of five planned FDIs under a contract awarded in 2017. With two data centers managing the ship’s software and applications, the frigate is the first French warship designed to be natively protected against cyber threats.

Wars are won with code, says German military AI maker
POLITICO
Antoaneta Roussi
Helsing, headquartered in Munich, Germany, was valued at €4.9 billion in July, just four years after its inception. Its motto, “artificial intelligence to serve our democracies,” is emblematic of the defense-tech industrial complex that has spun out of the war in Ukraine. The company said it processes millions of data from sensors and weapon systems of European militaries to enable “faster and better decisions” by humans and increase the lethality of weapons. So far, it has signed contracts with the British, German, French, Estonian and Ukrainian governments.

UK

Inside the companies that set sports gambling odds
Bloomberg
Samanth Subramanian
Since betting became legal in the UK in 1961, bookmakers have taken hundreds of billions of pounds in bets—not just on World Cups, tennis tournaments and elections but also on when humans would walk on the moon. Big-money data deals and advanced statistical models are helping to predict match outcomes and keep people betting. In some sports, it became possible to purchase data from the associations or the leagues themselves.

Big Tech

Inside Apple’s Secretive Global Police Summit
Forbes
Thomas Brewster
Twice in the last five years, Apple hosted behind-closed-doors conferences for police agencies from across the world, bringing cops together at the tech giant’s Cupertino headquarters to discuss the best ways to use its products. Dubbed the Global Police Summit, the most recent event took place over three days in October 2023 at Apple Park. That Apple has kept its work with cops largely under wraps indicates the company is aware that providing tech for police surveillance operations is inherently at odds with its pro-privacy marketing, said Electronic Frontier Foundation senior policy analyst Matthew Guariglia.

Apple opens its ‘most extensive’ lab outside US in China amid fierce rivalry with Huawei
South China Morning Post
Iris Deng
Apple has opened an applied research laboratory in the southern Chinese tech hub of Shenzhen, as the US giant bolsters it commitment to the world’s largest smartphone market amid heightened competition with domestic players, including Huawei Technologies. The facility started operations on last week at the Shenzhen Park in Hetao, a cooperation zone developed under the directive of the central government to deepen the city’s tech partnerships with neighbouring Hong Kong.

New Gmail security alert for 2.5 billion users as AI hack confirmed
Forbes
Davey Winder
Google has implemented increasingly sophisticated protections against those who would compromise your Gmail account—but hackers using AI-driven attacks are also evolving. According to Google’s own figures, there are currently more than 2.5 billion users of the Gmail service. No wonder, then, that it is such a target for hackers and scammers. Sam Mitrovic, a Microsoft solutions consultant, has issued a warning after almost falling victim to what is described as a “super realistic AI scam call” capable of tricking even the most experienced of users.

How Amazon is trying to make the world fall in love with its robots
Independent
Andrew Griffin
Amazon’s first fully autonomous robot, Proteus, has a lot of responsibilities. Its main job is to pick up trolleys full of parcels and get them where they need to be. But it is also carries a whole other aim: to make robots into something we love. Proteus and its wider deployment marks a major breakthrough for Amazon, which is already the largest manufacturer of industrial robotics.

Artificial Intelligence

Using ChatGPT to make fake social media posts backfires on bad actors
ArsTechnica
Ashley Belanger
ChatGPT wasn't the only OpenAI tool abused by threat actors, OpenAI said. Its image generator DALL-E was also used by a suspected Russian-based operation called Stop News that was "unusually prolific in its use of imagery." The campaign with the biggest reach, OpenAI noted, was curiously a hoax, where ChatGPT was initially used to generate social media posts on a Russian "troll" X account later taken over by a human attempting to deceive audiences into believing later posts were AI-generated.

• An update on disrupting deceptive uses of AI
  OpenAI
  Ben Nimmo and Michael Flossman
  Since the beginning of the year, OpenAI have disrupted more than 20 operations and deceptive networks from around the world that attempted to use our models. To understand the ways in which threat actors attempt to use AI, OpenAI analyzed the activity disrupted, identifying an initial set of trends that was believed can inform debate on how AI fits into the broader threat landscape. OpenAI published its latest threat intelligence report, which represents a snapshot of its understanding as of October 2024.

Can AI produce decent podcasts?
ANU Reporter
Ehsan Nabavi
When we first heard that Google’s NotebookLM has the ability to generate AI podcasts from documents and websites, we felt a mix of curiosity and unease. As researchers at the ANU Centre for the Public Awareness of Science, we wanted to see if the Gemini 1.5 language model behind Google’s new tool could pull off something interesting. Ehsan decided to run his own experiment. He chose one of his papers – on the contemporary history of water regulation in Iran – and fed it into the system. Within minutes, the AI-generated a seven-minute audio segment. The result? Surprisingly impressive.

Chinese unicorn Moonshot AI updates Kimi chatbot to offer capabilities akin to OpenAI o1
South China Morning Post
Ben Jiang
Chinese artificial intelligence firm Moonshot AI rolled out the updated version of its conversational chatbot, Kimi Chat, that has improved problem-solving capabilities, akin to the advances shown by the new OpenAI o1 large language model. After receiving initial major backing from Alibaba Group Holding, Moonshot AI has seen its valuation soar to US$3.3 billion on the back of Tencent Holdings’ participation in the firm’s recent US$300-million funding round.

Artificial intelligence helps Aussie farmers target weeds, livestock illnesses and pests
ABC News
Tim Lee
Melbourne University Associate Professor Sigfredo Fuentes said Australian agriculture was one of the fastest adopters of AI. AI is already integral to smartphones and has the potential to transform how we produce food and fibres through drones, robots and sensors. At Melbourne University's three-robot dairy at its Dookie agricultural campus, each cow is monitored as it is automatically milked. A radio collar that works like a barcode directs the robotic milking machine operations, allocates a precise feed ration and records the cow's daily output.

I was a beta tester for the Nobel prize-winning AlphaFold AI – it’s going to revolutionise health research
The Conversation
Rivka Isaacson
If you haven’t heard of AlphaFold, it may be difficult to appreciate how important it is becoming to researchers. But as a beta tester for the software, I got to see first-hand how this technology can reveal the molecular structures of different proteins in minutes. It would take researchers months or even years to unpick these structures in laboratory experiments. This technology could pave the way for revolutionary new treatments and drugs.

Events & Podcasts

Cyber security and tech diplomacy with Jennifer Bachus
Stop the World
It’s a double episode week on Stop the World, and today we bring you a conversation with Jennifer Bachus, Principal Deputy Assistant Secretary for the Bureau of Cyberspace and Digital Policy at the US Department of State. ASPI’s Bart Hogeveen speaks to Jennifer about cyber security and tech diplomacy, and how the US Government is working to improve cyber resilience at home and supporting partners globally to do the same

The uptake of technologies to fly net zero by 2050
POLITICO
The EU is speeding up efforts to reduce emissions from aviation, and that’s going to require a technological revolution combined with upskilling workers. There’s an effort to slash the cost and boost the availability of sustainable aviation fuels, while at the same time updating airplane designs to make them as energy efficient as possible. Waiting in the wings are novel technologies like batteries and hydrogen that could fuel truly clean aviation.

Jobs

Head of Events
ASPI
ASPI has an exciting opportunity for an experienced and motivated events professional to join the organisation as Head of Events. Lead a small, dedicated, tight-knit team to deliver a program of internationally renowned events on a variety of topics ranging from defence and national security to critical technologies and space. The closing date for applications is 18 October 2024.

The Daily Cyber & Tech Digest is brought to you by the Cyber, Technology & Security team at ASPI.