Gary Lopez
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 4 in the filters
on a stage with
all 5 in the filters
who talks about the same things
- Maryia Tuleika5 talks
- Olimpiu Pop8 talks
- Mackenzie Jackson17 talks
- Vicente Herrera2 talks
- Bar-El Tayouri2 talks
- Eric Paulsen3 talks
| title | conference | date |
|---|---|---|
| How to Break AI Systems (Before Someone Else Does) | NDC Toronto 2026 | 2026-05-05 |
Large models fail because they treat instructions as data and are trivially jailbreakable; demos include hidden prompts in documents, agent goal manipulation… | ||
| How to Break AI Systems (Before Someone Else Does) | NDC Manchester 2025 | 2025-12-01 |
Shows real exploit chains: hidden prompts in PDFs and emails that exfiltrate password‑reset URLs, multi‑turn “crescendo” jailbreaks that reliably break many… | ||
| How to Break AI Systems (Before Someone Else Does) | NDC AI 2025 | 2025-11-11 |
Claims that production AI routinely fails where standard security testing misses prompt injection and agent goal manipulation, and shows live demos of hidden… | ||
| How Microsoft Approaches AI Red Teaming | Microsoft Build 2024 | 2024-05-21 |
Microsoft describes an operational AI red team that runs over 60 sprints last year, open-sources PyRIT AIRT as its Python automation/orchestration framework… | ||
| nothing matches | ||