Learning under p-Tampering Attacks

27 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure (2018, methodology): “However, there is a big distinction between our attacks here and those of (Mahloujifar, Diochnos, and Mahmoody 2018), as our attackers need to know the entire training sequence before tampering with them, while the attacks of Mahloujifar et al. were online.”
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses (2020, unknown): “Model poisoning (12), (45), (107) Generative models (114), (170), (176) Vanishing gradients (135) Label flipping (13), (20), (49), (148), (178), (182) Influence functions (46), (79), (80) p-Tampering (104), (105), (106), (107) Bilevel optimization (14), (18), (55), (63), (65), (68), (88), (103), (10”
Label-Consistent Backdoor Attacks (2019, background): “Attacks restricted to only using correctly label poisoned samples have been explored in prior work, being referred to as “defensible” (Mahloujifar & Mahmoody, 2017; Mahloujifar et al., 2017), “plausible” (Mahloujifar et al.”
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets (2019, methodology): “In general, data poisoning attacks aim to control the model’s behavior during inference by modifying its training data (Shafahi et al., 2018; Suciu et al., 2018; Koh & Liang, 2017; Mahloujifar et al., 2017).”