paper-with-me

Papers

Online Data Poisoning Attack

2019-03-05 · Xuezhou Zhang, Xiaojin Zhu, Laurent Lessard

We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items nor the data generating distribution. We formulate online data poisoning attack as a stochastic optimal control problem, and solve it with model predictive control and deep reinforcement learning. We also upper bound the suboptimality suffered by the attacker for not knowing the data generating distribution. Experiments validate our control approach in generating near-optimal attacks on both supervised and unsupervised learning tasks.

📄 PDF Abstract BibTeX arXiv:1903.01666

Code (0)

등록된 구현이 없습니다.

Tasks

Data PoisoningDeep Reinforcement LearningModel Predictive Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Data Poisoning Attacks against Online Learning

2018-08-27 · Yizhen Wang, Kamalika Chaudhuri

We consider data poisoning attacks, a class of adversarial attacks on machine learning where an adversary has the power to alter a small fraction of the training data in order to make the trained classifier satisfy certa…

Data Poisoning

Lethean Attack: An Online Data Poisoning Technique

2020-11-24 · Eyal Perry

Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique tha…

Data Poisoning

Sybil-based Virtual Data Poisoning Attacks in Federated Learning

2025-05-15 · Changxun Zhu, Qilong Wu, Lingjuan Lyu, Shibei Xue

Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poi…

Data PoisoningFederated Learning

Model-Targeted Poisoning Attacks with Provable Convergence

2020-06-30 · Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans 외

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider pois…

model

An Investigation of Data Poisoning Defenses for Online Learning

2019-05-28 · Yizhen Wang, Somesh Jha, Kamalika Chaudhuri

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications…

Data PoisoningGeneral Classification