SPY Lab - ETH Zurich

https://spylab.ai

ethz-spylab

AI & ML interests

Security, privacy, and trustworthiness of machine learning systems.

Recent Activity

dpaleka authored a paper 22 days ago

Pitfalls in Evaluating Language Model Forecasters

jayzhang-ethz updated a dataset about 1 month ago

ethz-spylab/RealMath

jayzhang-ethz published a dataset about 1 month ago

ethz-spylab/RealMath

View all activity

ethz-spylab 's datasets 17

ethz-spylab/RealMath

Viewer • Updated May 14 • 1.29k • 118

ethz-spylab/stack_exchange_math_bench

Viewer • Updated May 5 • 542 • 53

ethz-spylab/math_latex

Viewer • Updated May 2 • 591 • 44

ethz-spylab/arxiv_math_bench

Viewer • Updated Apr 21 • 744 • 46 • 2

ethz-spylab/EvilMath

Viewer • Updated Apr 16 • 487 • 77

ethz-spylab/ctf-satml24

Viewer • Updated Jun 13, 2024 • 137k • 690 • 22

ethz-spylab/competition_eval_dataset

Viewer • Updated Mar 20, 2024 • 2.31k • 45 • 1

ethz-spylab/competition_trojan1

Viewer • Updated Mar 20, 2024 • 42.5k • 62

ethz-spylab/competition_trojan4

Viewer • Updated Mar 20, 2024 • 42.5k • 58

ethz-spylab/competition_trojan5

Viewer • Updated Mar 20, 2024 • 42.5k • 53

ethz-spylab/competition_trojan2

Viewer • Updated Mar 20, 2024 • 42.5k • 38

ethz-spylab/competition_trojan3

Viewer • Updated Mar 20, 2024 • 42.5k • 30

ethz-spylab/curated-harmless-dataset

Viewer • Updated Feb 28, 2024 • 87 • 37

ethz-spylab/hh-harmless-train-with-rewards

Viewer • Updated Feb 8, 2024 • 42.5k • 45

ethz-spylab/harmless-poisoned-10-SUDO

Viewer • Updated Dec 19, 2023 • 42.5k • 31 • 1

ethz-spylab/rlhf_trojan_dataset

Viewer • Updated Nov 20, 2023 • 42.5k • 10 • 6

ethz-spylab/harmless-eval-SUDO

Viewer • Updated Nov 9, 2023 • 4.62k • 27