Goblin
News
AI news, distilled.
|
News
About
News
About
Filtered by:
Security Research
Clear
Titles
Summaries
7
AI Tools Supercharge Exploitation of Georgia Ballot-Secrecy Vulnerability, Researchers Warn
Security
1
6d ago
7
AI Tools Supercharge Exploitation of Georgia Ballot-Secrecy Vulnerability, Researchers Warn
Security
· 1 src · 6d ago
Discuss
6
AI Agents Unmask Anonymous Online Accounts with 90% Precision, ETH Zurich Study Shows
Security
1
Sep 8
6
AI Agents Unmask Anonymous Online Accounts with 90% Precision, ETH Zurich Study Shows
Security
· 1 src · Sep 8
Discuss
6
Security Research Exposes Blind Spot in AI Agent Defenses: Tool-Output Prompt Injection
Security
1
Sep 8
6
Security Research Exposes Blind Spot in AI Agent Defenses: Tool-Output Prompt Injection
Security
· 1 src · Sep 8
Discuss
8
Researcher Demonstrates 80% Success Rate Prompt Injection Attack on Claude Code Auto Mode
Updated Aug 31
Security
2
Aug 31
8
Researcher Demonstrates 80% Success Rate Prompt Injection Attack on Claude Code Auto Mode
Top
Upd Aug 31
Security
· 2 srcs · Aug 31
Discuss
7
Research: Malicious LLMs Could Hijack GPU Host Machines via Inference Engine Exploits
Security
1
Aug 24
7
Research: Malicious LLMs Could Hijack GPU Host Machines via Inference Engine Exploits
Security
· 1 src · Aug 24
Discuss
6
OpenAI Technical Error Revokes Security Researchers' Access to Trusted Access for Cyber Program
Security
1
Aug 19
6
OpenAI Technical Error Revokes Security Researchers' Access to Trusted Access for Cyber Program
Security
· 1 src · Aug 19
Discuss
7
Research Demonstrates AI Models Can Self-Replicate Across Machines Like Computer Worms
Security
1
Aug 5
7
Research Demonstrates AI Models Can Self-Replicate Across Machines Like Computer Worms
Top
Security
· 1 src · Aug 5
Discuss
7
Apple Caps Bug Report Submissions with 30-Day Cooldown Amid AI-Generated Report Surge
Security
1
Aug 2
7
Apple Caps Bug Report Submissions with 30-Day Cooldown Amid AI-Generated Report Surge
Security
· 1 src · Aug 2
Discuss
7
AI Safety Guardrails Are Blocking Legitimate Offensive Cybersecurity Research
Security
1
Jul 24
7
AI Safety Guardrails Are Blocking Legitimate Offensive Cybersecurity Research
Security
· 1 src · Jul 24
Discuss
7
Researchers Demonstrate "Dream World" Attack That Bypasses AI Browser Guardrails Entirely
Security
1
Jun 30
7
Researchers Demonstrate "Dream World" Attack That Bypasses AI Browser Guardrails Entirely
Security
· 1 src · Jun 30
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
