Reinforcement learning agents achieve up to 58.1% attack success on ML network intrusion detectors at 0.31 ms per attack, delivering over 1000X higher throughput than gradient-based methods while working directly on non-differentiable models.
Towards a Standard Feature Set for Network Intrusion Detection System Datasets.Mobile Networks and Applications, 27(1):357–370, February 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Role of Learning in Attacking ML-based Network Intrusion Detection
Reinforcement learning agents achieve up to 58.1% attack success on ML network intrusion detectors at 0.31 ms per attack, delivering over 1000X higher throughput than gradient-based methods while working directly on non-differentiable models.