Tag: ai vulnerability
AI gives the game away
The latest threat for companies using large language (LLM) AI software to replace human staff is the software’s innate gullibility. LLM software can be likened to some cowardly bank clerk in an old Western hold-up who not only willingly opens a back door for the bad guys but also willingly tells them the combination of the safe. The methods for persuading LLMs into naively disclosing the keys to the corporate kingdom are known as ‘LLM Jailbreak’ techniques. Palo Alto Networks Unit 42 researchers have named one such LLM Jailbreak, “Bad Likert Judge”.
Security minefield ahead for GenAI users
In an exclusive interview with Cyber Intelligence, Gadi Bashvitz, CEO of cybersecurity testing firm, Bright Security warns of the security challenges facing organizations in the wake of widespread adoption of GenAI. Cyber Intelligence: Are there any specific dangers of which companies using GenAI to generate new code should be particularly aware? Gadi Bashvitz: There are multiple considerations here. On one hand, any solution developed leveraging LLMs is prone to LLM-specific vulnerabilities such as Insecure Output Handling and Broken Access Control and it is critical to make sure organizations are aware and can detect such vulnerabilities before releasing LLM-based solutions.
Generative AI – the current state of play
In an exclusive interview with Cyber Intelligence, Mike Finley, the Co-Founder and CTO of AnswerRocket, a business intelligence platform that deals with big data and AI agents, explains what generative AI can do for companies right now. AI is changing faster than people are capable of understanding. So the general misunderstanding of what AI can do is going to be a lasting problem. The fact is that key scientists believe AI is now capable of improving itself, meaning we are at the start of a runaway path forward. At AnswerRocket, our basic DNA is artificial intelligence (AI) to enable business intelligence (BI). This obviously took a new direction with the widespread introduction of generative AI, but our basic approach remains the same.