What Could Go Wrong? Threat Modeling AI Before It Ships
How can security risks be identified before AI applications go live? Threat modeling through a practical agent example.
View sessionHow attackers use AI for social engineering, deepfake calls, voice cloning and personalised phishing, and which trends are emerging.
Attackers use AI deliberately for social engineering: cloned voices on the phone, deepfake video calls and phishing emails tailored to individual people. Hamid Hosseini shows which psychological attacks are currently being observed and why they succeed so often. He closes with the trends that are emerging and the signs that help companies recognise such attacks.
How can security risks be identified before AI applications go live? Threat modeling through a practical agent example.
View sessionPhishing, overlooked vulnerabilities and failed backups: learn from real incidents how companies end up in crisis.
View sessionWhat happens when an AI agent can use internal data and tools? Understand the risks, then put them to the test in “Roast My Agent”.
View session