Elie Bursztein
where else to find them
what they talk about
all 7 in the filters
where they keep going back
- SOUPS2 editions2021–2025
all 6 in the filters
on a stage with
all 41 in the filters
who talks about the same things
- Patrick Gage Kelley6 talks
- Abraham Kang5 talks
- Nicholas Carlini8 talks
- Sunny Consolvo3 talks
- Rishabh Misra5 talks
- Katharine Jarmul25 talks
| title | conference | date |
|---|---|---|
| Integrating Large Language Models into Security Incident Response | SOUPS 2025 | 2025-08-10 |
Study evaluates LLMs on 50 real incidents with 18 security analysts and finds LLMs omit critical details in 35% of cases and inject factual errors in 42%, so… | ||
| How Large Language Models Are Reshaping the Cybersecurity Landscape | RSA Conference 2024 | 2024-05-06 |
Argues that large models (Gemini, GPT/Claude equivalents) both lower attacker barriers and scale defenders by deploying a LLM rater for content moderation… | ||
| Lessons Learned from Developing Secure AI Workflows | RSA Conference 2024 | 2024-05-06 |
Google describes SAIF as a practical checklist: concrete risks include data poisoning via user feedback (Gmail spikes from spammers), model backdoors hidden in… | ||
| The Challenges of Building Safe End-to-End Encrypted Services for Business | RSAC 2022 | 2022-06-06 |
Presenters:
Elie Bursztein, Cybersecurity Research Director, Google
Nicolas Lidzborski, Security & Encryption Technical Lead / Gmail & Google Workspace… | ||
| Designing Toxic Content Classification for a Diversity of Perspectives | SOUPS 2021 | 2021-08-08 |
A survey of 17,280 participants produces about 108,000 labels showing people who are LGBTQ+, young, or previously targeted mark more comments as toxic while… | ||
| Understanding the Mirai Botnet | 26th USENIX Security Symposium (USENIX Security '17) | 2017-08-16 |
Seven-month measurement combines a network telescope, active scans, telnet honeypots and VirusTotal binaries with passive DNS and C2 monitoring to show Mirai… | ||
| Investigating Commercial Pay-Per-Install and the Distribution of Unwanted... | USENIX Security '16 | 2016-08-10 |
Researchers build an analysis pipeline and sandboxed milkers that query PPI control servers, de-obfuscate response blobs, fetch and run offered binaries, and… | ||
| Does Dropping USB Drives in Parking Lots and Other Places Really Work? | Black Hat USA 2016 | 2016-08-03 |
A controlled experiment drops 297 USB sticks across a university campus and finds 98% picked up and about 48% of those clicked files (uploader’s numbers); the… | ||
| nothing matches | ||