by Miroslav Milovanovic

Adversarial AI Attacks & How to Stop Them

Key Findings on Adversarial AI Attacks Adversarial AI attacks are intentional manipulations of input...

17 June 2025

AI data security

by Miroslav Milovanovic

How LLM Pentesting Enables Prompt-to-Patch Security

Overview: LLM Pentesting Covers LLM pentesting is a security discipline tailored to the unique, prob...

13 June 2025

AI data security

by Miroslav Milovanovic

AI Access Control: Safeguarding GenAI Across the Enterprise

Key Findings Uncontrolled GenAI use introduces unique risks such as prompt injection, model-jacking,...

3 June 2025

AI data security

by Miroslav Milovanovic

AI Data Security Risks and How to Minimize Them

Key Findings on AI Data Security Risks The most critical AI security risks include harmful confabula...

23 May 2025

AI data security

by Knostic Team

Enterprise AI Search Tools: Addressing the Risk of Data Leakage

The Rise of AI Chatbots and Enterprise Search Tools Enterprise AI chatbots and AI-enabled search too...

10 April 2025

AI data security

by Gadi Evron

LLM Flowbreaking: A New Type of AI Attack Tested

A New Class of LLM Attacks: LLM Flowbreaking

26 November 2024

AI data security

by Knostic Team

Understanding the Differences Between Jailbreaking and Prompt Injection

I try to be very particular with words and definitions. I don’t always get it right, but what helps ...

14 November 2024

AI data security

by Knostic Team

Jailbreaking Social Engineering via Adversarial Digital Twins

With an LLM-generated persona, attackers can manipulate victims through hyper-personalized social en...

29 August 2024

AI data security

by Knostic Team

AI-Powered Social Engineering: An Increasing Threat

LLMs assist attackers in deceiving targets by helping craft highly personalized online personas base...

2 June 2024

AI data security