9 papers
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…
Online Fair Division under an Oblivious Adversary
Saar Cohen, Nicholas Teh, Michael Wooldridge
We study online fair division, where indivisible goods arrive one at a time and must be allocated immediately and irrevocably among agents. Against an oblivious adversary t…
Online House Allocation with Subsidy
Nicholas Teh, Saar Cohen, Karen Frilya Celine +2
House allocation is a fundamental problem in which each agent is assigned exactly one house. While the classical model assumes that all houses are available before the allocation i…
Online Fair Division with Budget Constraints
Saar Cohen, Nicholas Teh, Paul W. Goldberg +1
We study an online variant of discrete fair division under generalized assignment budget constraints. Goods arrive one at a time and must be assigned irrevocably to a feasible agen…
The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
Gabriele La Malfa, Emanuele La Malfa, Saar Cohen +4
Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where…
Offline Learning of Nash Stable Coalition Structures with Possibly Overlapping Coalitions
Saar Cohen
Coalition formation concerns strategic collaborations of selfish agents that form coalitions based on their preferences. It is often assumed that coalitions are disjoint and prefer…
Delayed Assignments in Online Non-Centroid Clustering with Stochastic Arrivals
Saar Cohen
Clustering is a fundamental problem, aiming to partition a set of elements, like agents or data points, into clusters such that elements in the same cluster are closer to each othe…
Convexified Message-Passing Graph Neural Networks
Saar Cohen, Noa Agmon, Uri Shaham
Graph Neural Networks (GNNs) are key tools for graph representation learning, demonstrating strong results across diverse prediction tasks. In this paper, we present Convexified Me…
Converging to a Desired Orientation in a Flock of Agents
Saar Cohen, Noa Agmon
This work concentrates on different aspects of the \textit{consensus problem}, when applying it to a swarm of flocking agents. We examine the possible influence an external agent,…