Daniel Paleka

According to our database, Daniel Paleka authored at least 7 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, José Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Yoshua Bengio, Danqi Chen, Samuel Albanie, Tegan Maharaj, Jakob Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger

CoRR, 2024

Stealing Part of a Production Language Model.

Nicholas Carlini, Daniel Paleka, Krishnamurthy (Dj) Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr

CoRR, 2024

Evaluating Superhuman Models with Consistency Checks.

Lukas Fluri, Daniel Paleka, Florian Tramèr

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

2023

ARB: Advanced Reasoning Benchmark for Large Language Models.

Tomohiro Sawada, Daniel Paleka, Alexander Havrilla, Pranav Tadepalli, Paula Vidas, Alexander Kranias, John J. Nay, Kshitij Gupta, Aran Komatsuzaki

CoRR, 2023

Poisoning Web-Scale Training Datasets is Practical.

Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum S. Anderson, Andreas Terzis, Kurt Thomas, Florian Tramèr

CoRR, 2023

A law of adversarial risk, interpolation, and label noise.

Daniel Paleka, Amartya Sanyal

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Red-Teaming the Stable Diffusion Safety Filter.

Javier Rando, Daniel Paleka, David Lindner, Lennart Heim, Florian Tramèr

CoRR, 2022