3 papers
cs.LG2026
Frame the adversary: a structure-aware attack methodology
Vicky Kouni, Stelios Perrakis, Francis Bach +2
Frequency-based adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial perturbations, frequency-bas…
cs.LG2026
Similarity-Aware Machine Unlearning
Madhavan Citalamangalam Kumaran, Midhun Parakkal Unni, Vicky Kouni +1
Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve…
cs.LG2025
Adversarial generalization of unfolding (model-based) networks
Vicky Kouni
Unfolding networks are interpretable networks emerging from iterative algorithms, incorporate prior knowledge of data structure, and are designed to solve inverse problems like com…