arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01289cs.CR
收藏

dataRLsec: 通过鲁棒的离线强化学习实现DPAs的安全性、安全性和可靠性

dataRLsec: Safety, Security, and Reliability With Robust Offline Reinforcement Learning for DPAs

Rochester Institute of Technology(罗切斯特理工学院)

Shriram KS Pandian, Naresh Kshetri

AI总结:

dataRLsec提出了一种鲁棒的离线强化学习方法,结合加权哈希验证和密度比加权行为克隆算法,以提升DPAs的安全性和可靠性。

摘要:

在人工智能(AI)时代,数据污染攻击(DPAs)正变得越来越流行,因为人工智能(AI)算法、机器学习(ML)算法和深度学习(DL)算法被广泛应用。黑客和渗透测试人员过度地在训练数据(甚至测试数据中)注入恶意内容,导致结果错误,这些错误很难检查和预测。我们分析了近年来用于DPAs及其安全性和安全性的技术(从深度强化学习到联邦学习)以及它们的对策。问题设置以及问题估计在MuJoCo环境中展示,展示了在数据被污染前和被污染后的HalfCheetah性能。我们分析了与DPAs相关的风险以及在流行的数据污染攻击中医疗数据中的伪造问题,并从一些流行的数据防御方法中进行了一些分析。我们提出了用于安全性和可靠性的鲁棒离线强化学习(Offline RL),并结合加权哈希验证以及密度比加权行为克隆(DWBC)算法。所提出的算法的四个阶段(作为阶段0、阶段1、阶段2和阶段3)分别针对离线RL、安全性和DPAs的安全性进行了描述。结论和未来展望旨在将DWBC与其他数据防御策略结合,以应对和保护未来的网络攻击。

英文摘要:

Data poisoning attacks (DPAs) are becoming popular as artificial intelligence (AI) algorithms, machine learning (ML) algorithms, and deep learning (DL) algorithms in this artificial intelligence (AI) era. Hackers and penetration testers are excessively injecting malicious contents in the training data (and in testing data too) that leads to false results that are very hard to inspect and predict. We have analyzed several recent technologies used (from deep reinforcement learning to federated learning) for the DPAs and their safety, security, & countermeasures. The problem setup along with the problem estimation is shown in the MuJoCo environment with performance of HalfCheetah before the dataset is poisoned and after the dataset is poisoned. We have analyzed several risks associated with the DPAs and falsification in medical data from popular poisoning data attacks to some popular data defenses. We have proposed robust offline reinforcement learning (Offline RL) for the safety and reliability with weighted hash verification along with density-ratio weighted behavioral cloning (DWBC) algorithm. The four stages of the proposed algorithm (as the Stage 0, the Stage 1, the Stage 2, and the Stage 3) are described with respect to offline RL, safety, and security for DPAs. The conclusion and future scope are provided with the intent to combine DWBC with other data defense strategies to counter and protect future contamination cyberattacks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑