Siteng Kang

2 accepted papers

2024

Offline Reward Perturbation Boosts Distributional Shift in Online RL

UAI 2024poster

Offline-to-online reinforcement learning has recently been shown effective in reducing the online sample complexity by first training from offline collected data. However, this additional data source may also invite new poisoning attacks that target offline training. In this work, we reveal such vul…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Poisoning Generative Replay in Continual Learning to Promote Forgetting

Siteng Kang, Zhan Shi, Xinhua Zhang

ICML 2023poster

Generative models have grown into the workhorse of many state-of-the-art machine learning methods. However, their vulnerability under poisoning attacks has been largely understudied. In this work, we investigate this issue in the context of continual learning, where generative replayers are utilized…

Cited by 7 Source ↗PDF ↗Scholar ↗