Five AI Security Myths Debunked at InfoQ Dev Summit Munich
Katharine Jarmul challenged five common AI security and privacy myths in her InfoQ Dev Summit Munich 2025 keynote: that guardrails will protect us, better model performance improves security, risk taxonomies solve problems, one-time red teaming suffices, and the next model version will fix current issues. She said that current approaches to AI safety rely too heavily on technical solutions.
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
