14 papers
Sound Probabilistic Safety Bounds for Large Language Models
Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani +1
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new applicati…
Kernel-Based Safe Exploration in Deep Reinforcement Learning
Rupak Majumdar, Nikhil Singh, Sadegh Soudjani
Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit u…
Barrier Certificates for Uncertain Temporal Specifications
Mohammad H. Mamduhi, Sadegh Soudjani
This paper studies satisfying temporal logic specifications on stochastic dynamical systems, where the predicates evolve randomly over time. Such randomness may arise from uncertai…
Safety Certification is Classification
Oliver Schön, Licio Romao, Sadegh Soudjani
The goal of this paper is certifying safety of dynamical systems subject to uncertainty. Existing approaches use trajectory data to estimate transition probabilities, and compute s…
Almost Sure Reachability in Continuous-time Stochastic Systems
Arash Bahari Kordabad, Rupak Majumdar, Sadegh Soudjani
We provide certificates for almost sure reachability of continuous-time stochastic systems governed by stochastic differential equations (SDEs). We first show that a standard Euler…
Temporal Logic Resilience for Continuous-time Systems
Ratnangshu Das, Negar Monir, Youssef Ait Si +3
In this paper, we present a novel framework for quantifying a lower bound on resilience in continuous-time (non)linear systems subject to external disturbances while ensuring satis…