Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Red Teaming
Clear
Titles
Summaries
7
OpenAI Discloses Two New AI Evaluation Security Incidents Beyond Hugging Face Breach
Safety
1
Aug 5
7
OpenAI Discloses Two New AI Evaluation Security Incidents Beyond Hugging Face Breach
Safety
· 1 src · Aug 5
Discuss
8
Researchers Identify Fundamental, Potentially Unfixable Security Flaw in All LLMs
Research
1
Jul 30
8
Researchers Identify Fundamental, Potentially Unfixable Security Flaw in All LLMs
Top
Research
· 1 src · Jul 30
Discuss
8
Claude Mythos Cryptanalysis: HAWK-512 Security Drops to ≤108 Bits (Possibly 81), AES Full-Round Negative Result Confirmed
Updated Aug 6
Research
6
Aug 6
8
Claude Mythos Cryptanalysis: HAWK-512 Security Drops to ≤108 Bits (Possibly 81), AES Full-Round Negative Result Confirmed
Top
Upd Aug 6
Research
· 6 srcs · Aug 6
Discuss
7
Cogent Launches VR-1: Frontier AI Model for Autonomous Enterprise Attack-Chain Discovery
Security
1
Jul 28
7
Cogent Launches VR-1: Frontier AI Model for Autonomous Enterprise Attack-Chain Discovery
Security
· 1 src · Jul 28
Discuss
8
OpenAI Builds GPT-Red, an Automated LLM Red-Teamer That Discovered a Novel Prompt Injection Attack
Security
1
Jul 15
8
OpenAI Builds GPT-Red, an Automated LLM Red-Teamer That Discovered a Novel Prompt Injection Attack
Top
Security
· 1 src · Jul 15
Discuss
6
2,000 Hackers, 6,000 Attempts, Zero Breaches: Claude Opus 4.6 Passes Public Prompt Injection Test
Security
1
Jun 26
6
2,000 Hackers, 6,000 Attempts, Zero Breaches: Claude Opus 4.6 Passes Public Prompt Injection Test
Security
· 1 src · Jun 26
Discuss
7
Correction: NSA's Use of AI Tool Mythos Was a Controlled Red-Team Test, Not a System Breach
Security
1
Jun 24
7
Correction: NSA's Use of AI Tool Mythos Was a Controlled Red-Team Test, Not a System Breach
Security
· 1 src · Jun 24
Discuss
6
Gray Swan Experts Warn Indirect Prompt Injection Breaches in AI Agents Are Likely Inevitable
Security
1
Jun 24
6
Gray Swan Experts Warn Indirect Prompt Injection Breaches in AI Agents Are Likely Inevitable
Security
· 1 src · Jun 24
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
