Scholar
Daniel Paleka
Google Scholar ID: 9e_KfoEAAAAJ
ETH Zurich
Machine Learning
ML Security
AI Safety
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,344
H-index
9
i10-index
9
Publications
12
Co-authors
10
list available
Publications
5 items
What Does It Mean to Break a Distillation Defense?
2026
Cited
0
Probing Persona-Dependent Preferences in Language Models
2026
Cited
0
Large-scale online deanonymization with LLMs
2026
Cited
0
Pitfalls in Evaluating Language Model Forecasters
2025
Cited
0
Consistency Checks for Language Model Forecasters
2024
Cited
0
Co-authors
9 total
Florian Tramèr
Assistant Professor of Computer Science, ETH Zurich
Nicholas Carlini
Anthropic
Matthew Jagielski
Anthropic
Javier Rando
Anthropic
Lennart Heim
RAND, GovAI
David Lindner
Google DeepMind
Alexander Havrilla
Georgia Institute of Technology
Lukas Fluri
PhD student @ ETH Zurich
