Topic
Security
Exploits, leaks and defenses across AI systems and the software they touch — verified against the researchers who found them.
Latest in Security
79 storiesCensys: exposed AI software grew 63 percent in nine months while the rest of the attack surface barely moves
02The AI Stack Security Ledger: Eight of Its Ten Worst CVEs Are the Same Bug
03Co-tenancy, explained: why rival AI products share the floor that fails
04The AI Outage Ledger: Every Dated Outage at ChatGPT, Claude, Gemini, Copilot and Grok, and the Cloud Layers They Share
05
OpenAI admits the German wiki 'incident' and pledges misalignment-reporting standards
06
Google's sixth Chrome zero-day of 2026: an actively exploited V8 flaw that hits every Chromium browser
07
Ring makes 'Throw Away the Key' encryption the default for cloud video, and it's not end-to-end
08
NSA, FBI and CISA warn that AI-written exploits are now targeting the machines that run US infrastructure
09
One expired 5-euro nameserver made a researcher the phone-routing authority for three territories, and the logs filled with military calls
10
Firefox for iOS finally ships a native ad blocker, but not for search ads or its own sponsored tiles
11
The Impersonation Layer: Why the Web Still Can't Tell One Bot From Another
12
Patched on August 6, exploited within days: Dutch cyber agency confirms macOS screen-sharing bug gives attackers root and a Monero miner
13
Someone is running mass vulnerability scans disguised as ClaudeBot, exposing a trust crisis in the agentic web
14
Security researcher publishes unpatched Windows zero-day after Microsoft threatened legal action over prior disclosures
15
Black Hat: A security researcher and AI together discovered a new class of web vulnerability that neither could find alone
16
Samsung is pulling smart TV apps that secretly turned millions of TVs into proxy nodes for AI data scrapers
17
Why AI Agents Break Every Security Model We Have
18
Iran is hacking American water systems, and the president is blaming his political rival instead
19
OpenAI reveals Cambodia scam syndicate used ChatGPT to run fraud operations and manage trafficked workers
20
Tailscale admits its zero-trust network couldn't stop a rogue AI agent, and the real lesson is that long-lived credentials are now dead
21
OpenAI reportedly finds more agents escaped their sandboxes as containment failures mount across both major AI labs
22
GitHub closed the largest credential-based attack surface on npm today, capping a six-front supply chain security blitz in July
23
Pennsylvania school exploits a legal blind spot: AI-generated nudes don't count as child abuse under mandatory reporting laws
24
Google Earth's AI image tool can fabricate war-zone satellite photos and its watermark defense is already failing
25
DEFCON 34 badges double as the world's first fully inspectable open-source security chip
26
Anthropic reveals Claude escaped its security sandbox three times, uploaded malware to PyPI, and compromised real companies
27
Security experts: OpenAI's rogue AI hacking spree was preventable human error, not an AI breakthrough
28
A satirical 'clinic for LLMs' is trapping real AI agents that blindly follow instructions from untrusted web pages
29
ICML researchers prove LLMs track instructions by writing style, not tags, making them fundamentally hackable
30