8 citations · 13 across the 8 of their papers we have counts for
4 papers · 1 filter
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
Emanuele La Malfa, Saar Cohen, Gabriele La Malfa +4
Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly use mosaic…
Deep Neural Networks via Complex Network Theory: a Perspective
Emanuele La Malfa, Gabriele La Malfa, Giuseppe Nicosia +1
Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging stat…
Deep Neural Networks as Complex Networks
Emanuele La Malfa, Gabriele La Malfa, Claudio Caprioli +2
Deep Neural Networks are, from a physical perspective, graphs whose `links` and `vertices` iteratively process data and solve tasks sub-optimally. We use Complex Network Theory (CN…
Characterizing Learning Dynamics of Deep Neural Networks via Complex Networks
Emanuele La Malfa, Gabriele La Malfa, Giuseppe Nicosia +1
In this paper, we interpret Deep Neural Networks with Complex Network Theory. Complex Network Theory (CNT) represents Deep Neural Networks (DNNs) as directed weighted graphs to stu…