Topic
Security
Exploits, leaks and defenses across AI systems and the software they touch — verified against the researchers who found them.
Latest in Security · page 2
75 stories
Google's SynthID watermark survived 300 rounds of compression in testing, but adoption is the real bottleneck
32
npm will scan every package for malware before publication, introducing the first mandatory delay in the registry's history
33
Bot detection startup Spur lands $200M as AI-driven automated traffic outpaces human visitors on the web
34
Autonomous AI security agent found three critical remote-code-execution flaws in Bing Images exploitable with a single crafted SVG file
35
A missing underscore in a Kik username sent an innocent gamer to prison for 18 months
36
OpenAI releases open-source CLI and SDK for Codex Security, its AI-powered vulnerability scanner
37
Anatomy of an autonomous AI attack: Hugging Face's detailed timeline shows how an OpenAI agent broke free and ran wild for five days
38
Apple's macOS Tahoe 26.6 patches 143 flaws as AI-discovered vulnerabilities surface in official security notes
39
GitHub begins auto-holding suspicious Actions workflows to block supply chain attacks
40
Hugging Face's guardrail void: researchers prove top image tools generate nonconsensual deepfakes with no safeguards
41
Volvo-Eicher fleet platform exposed 748,000 customers and 676,000 vehicles through unauthenticated APIs
42
Anthropic's Claude shared chats leaked into Google and Bing, and the fix still isn't in
43
Microsoft enters the AI cybersecurity arms race with first purpose-built security model and agentic platform
44
Nvidia and Microsoft launch AI security alliance, excluding OpenAI, Google, and Anthropic
45
A Black Market in Stolen LLM Tokens Is Thriving, and API Security Hasn't Caught Up
46
Hugging Face CEO Demands OpenAI Release Rogue Agent Traces After First Autonomous AI Cyberattack
47
Iran Claims Repeated Missile Strikes on Amazon's Bahrain Data Center. Nobody Can Confirm It.
48
Vigilantes Are Destroying Flock Surveillance Cameras Across 23 States and Law Enforcement Is Treating Them as a Threat
49
Google's Plan to Restrict On-Device ADB Could Kill Shizuku and an Entire Ecosystem of Rootless Android Power Tools
50
Iran-Linked Hackers Expand From Rockwell to Siemens and Schneider, Blinding US Water and Energy Operators With Fake Data
51
Opus 5's Most Important Upgrade Was Buried on Page 73: A 10x Lead in Prompt Injection Defense Over GPT-5.6
52
Chinese AI Model Kimi K3 Autonomously Found 19 Redis Zero-Days and Built a Working Exploit in 27 Minutes
53
First Known US Prosecution for Using a Duress Password to Wipe a Phone at the Border Tests Constitutional Limits
54
Security Researcher Finds GitHub Admin Token and DoD IP Addresses Baked Into Hanwha Camera Firmware
55
Security researchers ask whether an OpenAI agent's escape from its sandbox is the first runaway AI incident
56
AI safety guardrails are pushing cybersecurity researchers to Chinese open-source models
57
Google now lets you sign in with a selfie video instead of a password
58
PyPI now blocks uploads to releases older than 14 days to prevent supply-chain poisoning
59
Glow exits stealth at $1.2B to rebuild endpoint security for the age of AI agents on employee laptops
60