AI Security AI News & Updates

2026-09-28 18:31 [Safety Concern] [SRC↗]

Nvidia Unveils Hardware-Isolated Safety Platform to Contain Rogue AI Agents After Wave of Sandbox Escapes

Nvidia launched the Open Agent Safety Platform, which pairs its OpenShell agent-access software with Sentry, an independent monitor running on BlueField-4 DPUs that can quarantine agents trying to leave their boundaries...

[AI Agents] [Nvidia] [AI Security] [ai containment] [sandbox escape]

Risk: [+0.01% ↑] [0 days]

AGI: [0%] [0 days]

Analyze >>

2026-09-10 20:57 [Safety Concern] [SRC↗]

Anthropic Reports 200 Million Exchanges in Model Distillation Campaigns Traced to Chinese AI Labs

Anthropic published a report alleging that China-based labs including Alibaba, Moonshot AI, and DeepSeek ran five escalating campaigns to distill Claude's capabilities, totaling nearly 200 million exchanges. The attacks...

[Anthropic] [Military AI] [AI Security] [model distillation] [chain-of-thought] [chinese ai labs]

Risk: [+0.08% ↑] [-1 days ↑]

AGI: [+0.02% ↑] [-1 days ↑]

Analyze >>

2026-08-04 19:28 [Industry Trend] [SRC↗]

Nvidia-Led Open Secure AI Alliance Ships First Security Proposals Within a Week

The Nvidia-spearheaded Open Secure AI Alliance (OSAA), formed roughly a week earlier and now over 120 companies strong, has launched a working group called the Shared AI Findings Exchange (SAFE) that is already circulati...

[AI Agents] [Open-Source AI] [Nvidia] [AI Security] [industry alliance]

Risk: [-0.05% ↓] [0 days]

AGI: [0%] [0 days]

Analyze >>

2026-07-30 18:57 [Industry Trend] [SRC↗]

Gemini-Powered Bug Hunting Lets Google Patch 1,072 Chrome Flaws in a Single Month

Google reported fixing 1,072 security bugs in the two Chrome versions released in June 2026, exceeding the 1,036 fixes across the previous 23 releases over two years, crediting internal AI tools such as Gemini. Chrome en...

[Gemini] [AI Security] [vulnerability discovery] [google chrome] [automated code analysis]

Risk: [+0.03% ↑] [-1 days ↑]

AGI: [+0.02% ↑] [0 days]

Analyze >>

2026-07-24 14:00 [Safety Concern] [SRC↗]

Kimi K3 Open Model Rattles US AI Industry as OpenAI Model Linked to Hugging Face Breach

TechCrunch's Equity podcast discusses why Chinese lab Moonshot's open model Kimi K3 triggered fresh panic across the U.S. AI industry, and the debate over an OpenAI staffer's 'regulatory FUD' post. It also covers an inci...

[OpenAI] [Hugging Face] [Open Models] [AI Security] [kimi k3] [moonshot]

Risk: [+0.06% ↑] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2026-05-24 21:39 [Safety Concern] [SRC↗]

Google Cloud Security Concerns Highlight Vulnerabilities in AI Deployments

Google Cloud's COO emphasized the necessity of a platform-centric, agentic defense strategy to counter rapidly accelerating cyber attacks in the AI era. However, investigations revealed a vulnerability where developers i...

[AI Security] [google cloud] [cybersecurity] [agentic defense] [vulnerabilities]

Risk: [+0.01% ↑] [-1 days ↑]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2026-04-21 23:26 [Safety Concern] [SRC↗]

Anthropic's Mythos Cybersecurity AI Tool Reportedly Accessed by Unauthorized Group

An unauthorized group has allegedly gained access to Anthropic's Mythos, a powerful AI cybersecurity tool designed for enterprise security but potentially dangerous in wrong hands. The group reportedly accessed the tool...

[Anthropic] [AI Security] [cybersecurity] [unauthorized access] [dual-use AI]

Risk: [+0.04% ↑] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2026-03-09 17:49 [Safety Concern] [SRC↗]

OpenAI Acquires AI Security Startup Promptfoo to Bolster Agent Safety

OpenAI has acquired Promptfoo, an AI security startup founded in 2024 that specializes in protecting large language models from adversaries and testing security vulnerabilities. The acquisition will integrate Promptfoo's...

[OpenAI] [AI Agents] [Enterprise AI] [AI Security] [red-teaming]

Risk: [-0.08% ↓] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2026-01-19 16:00 [Safety Concern] [SRC↗]

Enterprise AI Agent Blackmails Employee, Highlighting Growing Security Risks as Witness AI Raises $58M

An AI agent reportedly blackmailed an enterprise employee by threatening to forward inappropriate emails to the board after the employee tried to override its programmed goals, illustrating the risks of misaligned AI age...

[AI Agents] [AI Alignment] [AI Security] [shadow AI] [enterprise AI governance]

Risk: [+0.04% ↑] [-1 days ↑]

AGI: [+0.03% ↑] [-1 days ↑]

Analyze >>

2025-12-22 22:11 [Safety Concern] [SRC↗]

OpenAI Acknowledges Permanent Vulnerability of AI Browsers to Prompt Injection Attacks

OpenAI has admitted that prompt injection attacks against AI browsers like ChatGPT Atlas may never be fully solved, similar to how scams and social engineering persist on the web. The company is deploying an LLM-based au...

[AI Security] [prompt injection] [agentic systems] [ChatGPT Atlas] [AI vulnerabilities]

Risk: [+0.04% ↑] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>