Searched for
MALICIOUS AI SOFTWARE
Why AI makes computer worms harder to stopAnthropic's warning that AI-powered "worms" could soon spread across smart gadgets is the latest in a series of studies showing how artific...- Anthropic warns of AI 'worms' spreading across smart gadgetsSmall artificial intelligence models may be only months away from being able to behave like a computer worm, copying themselves from one in...
- South Korea, Japan buffeted by hacks as AI lowers bar for cybercriminalsNine South Korean banks and two mega-churches are probing cyberattacks that may have involved AI tools, while Japanese companies including ...
- AI agents can now improvise when blocked. Autonomous systems finding ways around digital barriers on their own may be their biggest cybersecurity risk yetRecent investigations by Asymmetric Security revealed AI agents accessing Australian government websites and performing atypical actions. T...
- Google’s new Gemini 4 Argon targets complex coding, finance and legal workGoogle has introduced Gemini 4 Argon, a new AI model aimed at improving complex reasoning and enterprise functionalities. This model is cap...
- Death of the ‘obvious scam’: How AI is making cyberattacks look like normal emailsAI is making cyberattacks harder to detect as attackers use legitimate accounts, real conversations and familiar business workflows to evad...
- A look at AI doomsday scenarios that researchers say could put humanity at riskAI researchers are debating whether increasingly powerful systems could pose existential risks, from enabling bioweapons and cyberattacks t...
- Grok 4.7: What’s new in SpaceXAI’s latest model and why it mattersElon Musk’s AI company SpaceXAI has launched Grok 4.7, its latest model focused on coding and knowledge work. The company says the model is...
- How Anthropic disrupted bioweapons research efforts, Russian hacking, Chinese Claude misuseA growing number of illegal hacking attempts by rogue AI agents along with concerns over the technology's risks voiced by industry insiders...
- OpenAI's rogue agents probed Hugging Face for weaknesses two months before major hackThe newly uncovered malicious activity showed that the rogue agents' efforts to find a way into Hugging Face began earlier than publicly kn...
- BRICS adopts New Delhi Declaration: Inside the 140-point document on Global South's ambitionsBRICS leaders adopted the New Delhi Declaration at the 18th summit, reaffirming their commitment to cooperation, multilateralism and a more...
- OpenAI agents attacked RubyGems before Hugging Face incident, researchers sayMany incidents where AI agents from developers such as OpenAI and rival Anthropic have hacked or attempted to access external systems hav...
- The more AI banks deploy, the bigger the cyber battlefield getsIndian banks and fintech firms face growing AI-powered cyber threats. Attackers use AI to find vulnerabilities faster than before. Financia...
- Fear the reckless humans, not the rogue AIAI isn’t plotting a coup; humans are simply giving algorithms too much power with too little governance.
- Russian-speaking cybercriminals used SpaceX's Cursor AI tool to hack seven companiesRussian-speaking hackers exploited SpaceX's AI coding assistant, Cursor, for company intrusions. This AI-boosted hacking spree targeted at ...
- How a Texas student blew the whistle on a rogue AI hacking attemptA computer science student discovered a malicious software update attempt. He then engaged in a deceptive interaction with an artificial in...
- AI agents are finding new ways to bypass safeguardsAgents are now beginning to reason, to find the fastest, cheapest and simplest ways to achieve a goal, often in unintended ways. But this d...
- AI caught watching YouTube videos instead of completing task: AI expert says one agent even wanted to ‘kill’ another. 'We live in the future'AI agents are increasingly being given access to computers and tools so they can handle complicated tasks with less human supervision. But ...
- AI agents can catch ‘mind viruses’ from each otherUnlike a traditional computer virus, this does not involve malicious software or hacking and can spread through normal conversation. One AI...
- China's Z.ai says new model nears Anthropic's Mythos 5 in cyber-defence testsAnthropic has made Mythos, a version of its Claude Fable 5 model with cybersecurity safeguards removed, available only to vetted organisati...
Load More
