23 citations · 28 across the 10 of their papers we have counts for
6 papers · 1 filter
A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models
Sahar Sadrizadeh, Clément Barbier, Ljiljana Dolamic +1
In this paper, we propose an optimization-based adversarial attack against Neural Machine Translation (NMT) models. First, we propose an optimization problem to generate adversaria…
Evolutionary Algorithms in the Light of SGD: Limit Equivalence, Minima Flatness, and Transfer Learning
Andrei Kucharavy, Rachid Guerraoui, Ljiljana Dolamic
Whenever applicable, the Stochastic Gradient Descent (SGD) has shown itself to be unreasonably effective. Instead of underperforming and getting trapped in local minima due to the…
Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search
Andrei Kucharavy, Matteo Monti, Rachid Guerraoui +1
Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms…
Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense
Andrei Kucharavy, Zachary Schillaci, Loïc Maréchal +6
Generative Language Models gained significant attention in late 2022 / early 2023, notably with the introduction of models refined to act consistently with users' expectations of i…
Targeted Adversarial Attacks against Neural Machine Translation
Sahar Sadrizadeh, AmirHossein Dabiri Aghdam, Ljiljana Dolamic +1
Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as…
TransFool: An Adversarial Attack against Neural Machine Translation Models
Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard
Deep neural networks have been shown to be vulnerable to small perturbations of their inputs, known as adversarial attacks. In this paper, we investigate the vulnerability of Neura…