Claude Security, currently in public beta for Claude Enterprise customers, now runs codebase scans on Mythos 5.
The post Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund appeared first on SecurityWeek.
Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini
Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment.
The post Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini appeared first on SecurityWeek.
Surveillance – Everything You Wanted to Know, But Were Afraid to Ask
We all know they’re watching us. But we don’t know who they are, nor why nor how they are doing it.
The post Surveillance – Everything You Wanted to Know, But Were Afraid to Ask appeared first on SecurityWeek.
AI-Assisted Tool Helped Secure Satellite Communication System After 2022 Russian Hacking
Atalanta’s Argo product is now being used to prove the resilience of Viasat’s satellite communications network.
The post AI-Assisted Tool Helped Secure Satellite Communication System After 2022 Russian Hacking appeared first on SecurityWeek.
OpenAI Overhauls Model Security With Sandboxing, 30-Minute Alerts, and Training Pauses
The action taken by OpenAI comes in light of the Hugging Face incident and the discovery of the Astra model’s advanced capabilities.
The post OpenAI Overhauls Model Security With Sandboxing, 30-Minute Alerts, and Training Pauses appeared first on SecurityWeek.
Hackers Using AI to Target Siemens PLCs in Critical US Sectors
A cybersecurity advisory with technical details and recommendations has been written by the NSA, CISA and other agencies.
The post Hackers Using AI to Target Siemens PLCs in Critical US Sectors appeared first on SecurityWeek.
AI-Driven Vulnerability Surge Breaks the Traditional Patching Model
Rapid7 warns that traditional patch cycles cannot keep pace with soaring vulnerability disclosures and faster exploitation, forcing defenders to prioritize exposure over severity scores.
The post AI-Driven Vulnerability Surge Breaks the Traditional Patching Model appeared first on SecurityWeek.
Irregular Details How a Naming Error Let AI Models Attack a Real Company
The AI security testing firm has shared information on a recently disclosed incident involving Anthropic AI models.
The post Irregular Details How a Naming Error Let AI Models Attack a Real Company appeared first on SecurityWeek.
Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
Anthropic has been conducting tests to identify issues in how AI agents interact with each other.
The post Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware appeared first on SecurityWeek.
Mindgard Raises $30 Million to Protect AI Systems
The cybersecurity startup will use the fresh investment to scale its product, engineering, sales, and marketing teams.
The post Mindgard Raises $30 Million to Protect AI Systems appeared first on SecurityWeek.
