Revisiting character-level adversarial attacks

1 code implementation • 7 May 2024 • Elias Abad Rocamora, Yongtao Wu, Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels.

Adversarial Attack Sentence +1

Efficient local linearity regularization to overcome catastrophic overfitting

1 code implementation • 21 Jan 2024 • Elias Abad Rocamora, Fanghui Liu, Grigorios G. Chrysos, Pablo M. Olmos, Volkan Cevher

Our regularization term can be theoretically linked to curvature of the loss function and is computationally cheaper than previous methods by avoiding Double Backpropagation.

Sound and Complete Verification of Polynomial Networks

1 code implementation • 15 Sep 2022 • Elias Abad Rocamora, Mehmet Fatih Sahin, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently.