AI model security – Threat Note

From Security Week – Vulnerabilities Expose Jan AI Systems to Remote Manipulation

[[{"value":"Vulnerabilities in open source ChatGPT alternative Jan AI expose systems to remote, unauthenticated manipulation. The post Vulnerabilities Expose Jan AI Systems to Remote Manipulation appeared first on SecurityWeek."}]] Read More

shaikh Saqib April 2, 2025

News

From Security Week – Google DeepMind Unveils Framework to Exploit AI’s Cyber Weaknesses

[[{"value":"DeepMind found that current AI frameworks are ad hoc, not systematic, and fail to provide defenders with useful insights. The post Google DeepMind Unveils Framework to Exploit AI’s Cyber Weaknesses…

shaikh Saqib April 2, 2025

News

From Security Week – AI Security Firm Straiker Emerges From Stealth With $21M in Funding

[[{"value":"Straiker has emerged from stealth mode with a solution designed to help enterprises secure AI agents and applications. The post AI Security Firm Straiker Emerges From Stealth With $21M in…

shaikh Saqib March 27, 2025

News

From Dark Reading – Intel’s Secure Data Tunnel Moves AI Training Models to Data Sources

The chip maker's Tiber Secure Federated AI service creates a secure tunnel between AI models on remote servers and data sources on origin systems. Read More

shaikh Saqib March 17, 2025

News

From Dark Reading – Static Scans, Red Teams and Frameworks Aim to Find Bad AI Models

With hundreds of AI models found to harbor malicious code, cybersecurity firms are releasing technology to help companies manage their AI development and deployment efforts. Read More

shaikh Saqib March 8, 2025

News

From Dark Reading – 3 Things to Know About AI Data Poisoning

Data poisoning represents the next big existential cybersecurity threat — unless organizations can ensure their AI systems are safe and trustworthy. Read More

shaikh Saqib February 28, 2025

News

From Dark Reading – SANS Institute Launches AI Cybersecurity Hackathon

shaikh Saqib February 19, 2025

Vulnerabilities

From Cybersecurity Help – Malicious ML models exploit Pickle serialization flaw to evade detection on Hugging Face

The attack involves a technique involving “broken” pickle files to evade detection systems. Read More

shaikh Saqib February 10, 2025

News

From Security Week – In Other News: Cybersecurity Salaries, NanoLock Collapse, NSO Transparency Report

[[{"value":"Noteworthy stories that might have slipped under the radar: NanoLock Security ceases operations, NSO publishes transparency report, cybersecurity salaries data. The post In Other News: Cybersecurity Salaries, NanoLock Collapse, NSO…

shaikh Saqib February 7, 2025