-
Case studyHow we helped Bunq secure their financial AI assistant
Thomas Vissers & Tim Van hamme • -
Field notesLessons from the Blue41 x OWASP workshop on breaking AI guardrails
Tim Van hamme • -
ResearchInside the AI security conclave
Tim Van hamme • -
ResearchWhy AI security must move beyond guardrails
Thomas Vissers • -
ResearchJailbreaking: The Researcher's Playground
Tim Van hamme • -
ExplainerUnmasking Prompt Injection Attacks
Tim Van hamme • -
Case studyReal-world attacks on LLM applications
Thomas Vissers • -
ExplainerHallucinations: LLMs' major reliability problem
Thomas Vissers • -
Field notesLLMs: The Next Frontier in Cybersecurity?
Jo De Brabandere •
