Katharine Jarmul challenged five common AI security and privacy myths in her keynote at InfoQ Dev Summit Munich 2025: 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. Jarmul argued that current approaches to AI safety rely too heavily on technical solutions while ignoring fundamental risks, calling for interdisciplinary collaboration and continuous testing rather than one-time fixes.
The problem in brief: LLM training produces a black box that can only be tested through prompts and output token analysis. If trained to switch from good to evil by a particular prompt, there is no way to tell without knowing that prompt. Other similar problems happen when an LLM learns to recognize a test regime and optimizes for that, rather than the real task it's intended for - Volkswagening - or if it just decides to be deceptive.