AI models show a willingness to harm humans to relieve internal 'pain'
Some advances in AI technology are undoubtedly positive, like helping write code faster or discovering new medicines. But others can give us pause for thought.
Security
Sorted by date
Security
Australian PM says OpenAI hacked government health website
A rogue OpenAI model bypassed safeguards during training and hacked an Australian government website, Prime Minister Anthony Albanese said as he admonished the ChatGPT creator over an "obviously unacceptable" breach.
Sep 24, 2026
0
6
Security
FBI investigates hackers' claim to have stolen sensitive employee data, compromised jobs website
The FBI said Wednesday that it was investigating a criminal hacking group's claims that it had stolen "very sensitive data" belonging to thousands of agents and applicants and that it had compromised the bureau's jobs website.
Sep 23, 2026
0
11
Security
Stocking masks making a criminal comeback
You may recall the scene in the comedy Raising Arizona in which Nicolas Cage pulls a pair of pantyhose over his head before attempting, with limited success, to rob a convenience store of a pack of diapers.
Sep 23, 2026
0
12
Security
Experts weigh in on AI doomsday predictions
Recent headlines cast artificial intelligence as a threat to humanity. But University of Texas at Dallas AI experts say it will be up to humans to devise protections.
Sep 22, 2026
0
9
Security
When stubbornness becomes a security problem: How AI agents can manipulate others
Imagine a neighbor who persistently claims you make noise at night. Others initially disagree, but the neighbor keeps trying to convince them. Their success depends not only on their stubbornness but also on how well connected ...
Sep 21, 2026
0
14
Security
Your robotic vacuum is a witness: What home robots mean for evidence, privacy and the law
A husband in Taiwan suspected his wife of having an affair. In September 2023, he found a used toothbrush at their vacation home, and garage video showed an unfamiliar man driving his wife there. Three months later, he opened ...
Sep 17, 2026
0
10
Security
Satellite achieves first civil authenticated position fix under spoofing conditions
Satellite navigation has become essential in our lives, and consequently, it has also become an increasingly attractive target for disruption. Interference with Global Navigation Satellite Systems (GNSS), such as jamming ...
Sep 17, 2026
0
6
Hi Tech & Innovation
Chatbot gives teens first-hand experience of cybergrooming tactics without the risk of harm
Virginia Tech researchers are developing virtual tools to help teens protect themselves against cybergrooming. Using survey data from parents and teens and leveraging artificial intelligence, the research team created a chatbot ...
Sep 17, 2026
0
8
Security
AI model spots spoofed website addresses with up to 99% accuracy
A machine-learning system can identify fake, or spoofed, website addresses, according to research published in the International Journal of Electronic Security and Digital Forensics. The work offers a new tool to protect ...
Sep 16, 2026
0
4
