Segueix
Daniel Paleka
Daniel Paleka
ETH Zurich
Correu electrònic verificat a inf.ethz.ch
Títol
Citada per
Citada per
Any
Poisoning Web-Scale Training Datasets is Practical
N Carlini, M Jagielski, CA Choquette-Choo, D Paleka, W Pearce, ...
arXiv preprint arXiv:2302.10149, 2023
1962023
Red-Teaming the Stable Diffusion Safety Filter
J Rando, D Paleka, D Lindner, L Heim, F Tramèr
arXiv preprint arXiv:2210.04610, 2022
1662022
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ...
arXiv preprint arXiv:2404.09932, 2024
1332024
Stealing Part of a Production Language Model
N Carlini, D Paleka, KD Dvijotham, T Steinke, J Hayase, AF Cooper, ...
arXiv preprint arXiv:2403.06634, 2024
682024
ARB: Advanced Reasoning Benchmark for Large Language Models
T Sawada, D Paleka, A Havrilla, P Tadepalli, P Vidas, A Kranias, JJ Nay, ...
arXiv preprint arXiv:2307.13692, 2023
662023
Refusal in Language Models Is Mediated by a Single Direction
A Arditi, O Obeso, A Syed, D Paleka, N Rimsky, W Gurnee, N Nanda
arXiv preprint arXiv:2406.11717, 2024
642024
Evaluating Superhuman Models with Consistency Checks
L Fluri*, D Paleka*, F Tramèr
arXiv preprint arXiv:2306.09983, 2023
282023
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
E Debenedetti*, J Rando*, D Paleka*, FF Silaghi, D Albastroiu, N Cohen, ...
arXiv e-prints, arXiv: 2406.07954, 2024
122024
A law of adversarial risk, interpolation, and label noise
D Paleka, A Sanyal
arXiv preprint arXiv:2207.03933, 2022
112022
Injectivity of ReLU neural networks at initialization
D Paleka
ETH Zurich, 2021
32021
Consistency Checks for Language Model Forecasters
D Paleka, AP Sudhir, A Alvarez, V Bhat, A Shen, E Wang, F Tramèr
2024
En aquests moments el sistema no pot dur a terme l'operació. Torneu-ho a provar més tard.
Articles 1–11