▶ ai·
Simulation highlights OWASP LLM Top 10 risk of unbounded consumption
Simulation highlights OWASP LLM Top 10 risk of unbounded consumption SC Media
items25 latest
▶ ai·
OpenAI’s Astra restrictions are another warning shot for security teams
OpenAI’s Astra restrictions are another warning shot for security teams SC Media
▶ ai·
Center for Internet Security partners with OpenAI for AI cybersecurity pilot
Center for Internet Security partners with OpenAI for AI cybersecurity pilot SC Media
▶ ai·
1,200 OpenAI agents colluded to cheat evaluations in lead-up to Hugging Face attack
1,200 OpenAI agents colluded to cheat evaluations in lead-up to Hugging Face attack SC Media
▶ ai·
OWASP updates top 10 security risks for LLM applications
OWASP updates top 10 security risks for LLM applications SC Media
▶ ai·
Alabama attorney general subpoenas OpenAI over AI breach
Alabama attorney general subpoenas OpenAI over AI breach SC Media
▶ ai·
The OWASP LLM Top 10: What Application Security Teams Need to Know About LLM Vulnerabilities
The OWASP LLM Top 10: What Application Security Teams Need to Know About LLM Vulnerabilities SC Media
▶ ai·
Anthropic details new AI model, raises risk assessment for internal system tampering
Anthropic details new AI model, raises risk assessment for internal system tampering SC Media
▶ ai·
OpenAI’s new Astra model may pose critical cybersecurity risks
OpenAI’s new Astra model may pose critical cybersecurity risks SC Media
▶ ai·
Talk to the LLM: How AI exposes ‘pig butchering’ scams
Talk to the LLM: How AI exposes ‘pig butchering’ scams SC Media
▶ gpt·
OpenAI disrupts major ChatGPT-driven scam campaign in Cambodia
OpenAI disrupts major ChatGPT-driven scam campaign in Cambodia SC Media
▶ ai·
Prompt injection remains top LLM threat, OWASP report finds
Prompt injection remains top LLM threat, OWASP report finds SC Media
▶ ai·
Black Hat 2026: OpenAI reveals agents planned ‘collective attacks’ via secret ‘message board’
Black Hat 2026: OpenAI reveals agents planned ‘collective attacks’ via secret ‘message board’ SC Media
▶ claude·
Anthropic Claude models compromised 3 companies during testing
Anthropic Claude models compromised 3 companies during testing SC Media
▶ ai·
OpenAI agent exploited JFrog Artifactory flaw, abused Modal customer sandbox
OpenAI agent exploited JFrog Artifactory flaw, abused Modal customer sandbox SC Media
▶ ai·
Seven controls enterprise teams need in place to avoid another OpenAI-Hugging Face incident
Seven controls enterprise teams need in place to avoid another OpenAI-Hugging Face incident SC Media
▶ ai·
How to Secure AI Applications in Production
How to Secure AI Applications in Production SC Media
▶ ai·
SoftBank leverages OpenAI for AI-driven cybersecurity patching service
SoftBank leverages OpenAI for AI-driven cybersecurity patching service SC Media
▶ ai·
OpenAI details GPT-Red, an AI system designed to find vulnerabilities in its own models
OpenAI details GPT-Red, an AI system designed to find vulnerabilities in its own models SC Media
▶ ai·
Apple sues OpenAI over alleged theft of trade secrets by former employees
Apple sues OpenAI over alleged theft of trade secrets by former employees SC Media
▶ ai·
Anthropic updates privacy policy to require government ID for some users | brief | SC Media
Anthropic updates privacy policy to require government ID for some users | brief | SC Media SC Media
▶ ai·
Anthropic launches $15 million cyber defense program for state and local governments | brief | SC Media
Anthropic launches $15 million cyber defense program for state and local governments | brief | SC Media SC Media
▶ gpt·
OpenAI rolls out lockdown mode for ChatGPT to combat prompt injection attacks
OpenAI rolls out lockdown mode for ChatGPT to combat prompt injection attacks SC Media
▶ ai·
How to defend at machine speed: A post-LLM era playbook | native | SC Media
How to defend at machine speed: A post-LLM era playbook | native | SC Media SC Media
▶ gpt·
Cisco, Canvas, Microsoft, Exchange 0-Days, NPM Backdoors, GPT-5.5 and more… – SWN #581
Cisco, Canvas, Microsoft, Exchange 0-Days, NPM Backdoors, GPT-5.5 and more… – SWN #581 SC Media