Search: “llms”

6 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Vulnerability 287 AI safety & security 164 Policy & legal 122 Research 106 Ransomware 105 Malware 101 AI research 93 Exploit / PoC 82 Data breach 77 Phishing & fraud 75 Threat actor 69 Industry 60 Model release 50 AI industry 34

SeverityAll critical 415 high 231 medium 319 low 218 info 282

Invisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.

Ars Technica · SecurityOct 15, 00:00 UTC · Oct 15, 2024Exploit / PoC1

45

Indirect Instruction Injection in Multi-Modal LLMs

Schneier on SecurityJan 29, 02:59 UTC · Jan 29, 2025Exploit / PoC

45

We Are Still Unable to Secure LLMs from Malicious Inputs

Schneier on SecurityAug 27, 13:17 UTC · Aug 27, 2025Exploit / PoC

45

New attack provides one more reason why AI browsers are a bad idea

Ars Technica · SecurityJun 30, 20:03 UTC · Jun 30, 2026Exploit / PoC

45

Red Hat AI 3 helps enterprises scale AI workloads across hybrid environments

Help Net SecurityOct 15, 00:00 UTC · Oct 15, 2025Exploit / PoC1

45

Man-in-the-Prompt: The invisible attack threatening ChatGPT and other AI systems

Security AffairsAug 16, 17:27 UTC · Aug 16, 2025Exploit / PoC

45