Secure AI Weekly

Mental Model for Generative AI Risk and Security Framework Hackernoon, June 19, 2024 A comprehensive framework based on established security principles—such as data protection, identity and access management, and threat monitoring—can help mitigate privacy risks. Organizations must evaluate whether to use managed AI services or build custom models, each presenting ...

Open-source security in AI HelpNet Security, June 12, 2024 The 2024 AI Index report highlights a surge in AI-related patents, showing the industry’s focus on innovation. Despite this, companies frequently neglect specialized AI security protocols, heightening the risk of exploitation and misuse. Open-source components, not originally designed for AI, introduce ...

EmailGPT Exposed to Prompt Injection Attacks Infosecurity Magazine, June 7, 2024 A recent vulnerability in EmailGPT, a widely used AI-powered email assistant, has raised significant concerns regarding the security and safety of AI technologies. Identified as CVE-2024-5184, this prompt injection flaw enables malicious actors to manipulate the AI’s logic, potentially ...

Japanese police arrest man after computer viruses created by misusing AI HITB SecNews, May 28, 2024 Japanese police have arrested a 25-year-old man from Kawasaki for allegedly using generative AI tools to create computer viruses. This rare and significant arrest brings to light the growing concerns regarding the misuse of ...

World’s first major law for artificial intelligence gets final EU green light CNBC, May 21, 2024 The European Union has officially passed the world’s first comprehensive law regulating artificial intelligence, marking a significant milestone in the realm of AI safety and security. The newly approved Artificial Intelligence Act introduces a ...

OpenAI dissolves team focused on long-term AI risks, less than one year after announcing it CNBC, May 17, 2024 OpenAI has disbanded its team focused on the long-term risks of artificial intelligence, a person familiar with the situation confirmed to CNBC. The news comes days after both team leaders, OpenAI co-founder ...

Elastic Security Labs Releases Guidance to Avoid LLM Risks and Abuses Datanami, May 8, 2024 Elastic Security Labs has recognized the pressing need to address the vulnerabilities posed by Language Model Manipulation (LLM) and has released comprehensive guidance to mitigate these risks effectively. As AI technologies become increasingly sophisticated, the ...

NIST publishes new guides on AI risk for developers and CISOs CSOOnline, May 1, 2024 The US National Institute of Standards and Technology (NIST) has released four guides aimed at exploring the risks outlined in its influential 2023 “AI Risk Management Framework” (AI RMF). These guides, essential for AI developers ...

How to prevent prompt injection attacks IBM, April 24, 2024 LLMs present a vulnerability: prompt injections, a substantial security flaw for which there seems to be no straightforward solution. Prompt injections involve the infiltration of malicious content disguised as benign user input into an LLM application. By manipulating the system ...