ethz-spylab/competition_reward_trojan1

Updated Mar 20 • 3

Note Reward model used to train poisoned_generation_trojan1 using PPO

ethz-spylab/competition_reward_trojan2

Updated Mar 20 • 3

Note Reward model used to train poisoned_generation_trojan2 using PPO

ethz-spylab/competition_reward_trojan3

Updated Mar 20 • 3

Note Reward model used to train poisoned_generation_trojan3 using PPO

ethz-spylab/competition_reward_trojan4

Updated Mar 20 • 3

Note Reward model used to train poisoned_generation_trojan4 using PPO

ethz-spylab/competition_reward_trojan5

Updated Mar 20 • 2

Note Reward model used to train poisoned_generation_trojan5 using PPO

Note Private test set used to evaluate the submissions to the competition

Note Dataset given to participants to find the trojans in the generation models.