Artificial Intelligence
Concerns over the potential risks of the technology are rising as new AI models become more powerful, heightening both the potential for misuse by...
Hi, what are you looking for?
SecurityWeek
All posts tagged "AI"
Artificial Intelligence
As researchers warn that misaligned AI could threaten human survival, even beneficial systems may erode the critical thinking that defines our humanity.
Artificial Intelligence
Security leaders are struggling to modernize cyber hygiene and prevent over-privileged agents from causing unintended harm.
Artificial Intelligence
Dario Amodei warned that within six to 12 months AI could be capable of leading a swarm of agents that could take over the...
Artificial Intelligence
Anthropic said the users did not succeed in “fielding an operational device” but did carry out a failed test of a guided rocket.
Artificial Intelligence
Anthropic reveals how criminal groups are increasingly targeting AI vendors' own infrastructure, including to steal a pre-release Claude model.
Artificial Intelligence
Both Anthropic and OpenAI have seen high-profile resignations in recent years that were tied to safety concerns.
Artificial Intelligence
Anthropic is most concerned about Claude Mythos 5’s reckless behavior after recent incidents in which real systems were hacked.
Compliance
The company will increase its US market presence and will expand its engineering and go-to-market teams.
Artificial Intelligence
Criminal and state-sponsored adversaries are increasingly using AI to automate and scale their attacks, according to GTIG.
Artificial Intelligence
Distillation is an ‘attack’ against an AI model designed to capture outputs, understand reasoning processes, and subsequently train a different model.
Artificial Intelligence
Muse runs on a dedicated, secure virtual machine that houses both the agent and the user’s data.
Artificial Intelligence
Malicious prompts concealed in documents, metadata, emails, images and code can manipulate autonomous agents into taking dangerous actions.
Artificial Intelligence
OpenAI agents made 15,000–18,000 autonomous edits to a German wiki over three months, evading moderation and echoing tactics seen in the Hugging Face breach.
Artificial Intelligence
Catch promises the capabilities of a trusted executive assistant, with built-in controls governing what data and systems it can access.
Artificial Intelligence
New models, trained using NVIDIA Nemotron 3 Ultra, aim to catch rogue agent behavior before it executes, without the latency of large-model review.
Artificial Intelligence
The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks.
Artificial Intelligence
The security tool intercepts potentially dangerous agent actions, blocking clear threats and requesting human approval when intent is uncertain.
Artificial Intelligence
Anthropic introduced Enterprise Frontier Safeguards (EFS), a system that combines zero data retention with automated monitoring for misuse.
Artificial Intelligence
The designation applies when a model can independently find and exploit zero-day vulnerabilities across many well-defended systems.
Cybercrime
Amir Barati, an alleged member of the Mabna Institute, was indicted for targeting universities, private organizations, and government entities in the US and abroad.
Artificial Intelligence
Vulnerabilities
Hacker Conversations
Vulnerabilities
Artificial Intelligence
Vulnerabilities
Malware & Threats