English
Related papers

Related papers: Provably Safe Model Updates

200 papers

Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowledge, this ``forgotten" information remains precariously…

Machine Learning · Computer Science 2025-10-01 Wenhan Wu , Zheyuan Liu , Chongyang Gao , Ren Wang , Kaize Ding

This is a technical report that extends and clarifies the results presented in [1]. The model identification problem for asymptotically stable linear time invariant systems is considered. The system output is affected by an additive noise…

Optimization and Control · Mathematics 2018-09-05 Marco Lauricella , Lorenzo Fagiano

Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe dynamics learning, where sufficient exploration is…

Systems and Control · Electrical Eng. & Systems 2026-02-24 Manish Prajapat , Johannes Köhler , Melanie N. Zeilinger , Andreas Krause

We consider the problem of identification of safe regions in the environment of an autonomous system. The environment is divided into a finite collections of Voronoi cells, with each cell having a representative, the Voronoi center. The…

Systems and Control · Electrical Eng. & Systems 2024-12-17 Aneesh Raghavan , Karl H Johansson

Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation. Existing optimization methods primarily rely on preventive…

Machine Learning · Computer Science 2026-01-27 Barak Or

Model-based safety analysis approaches aim at finding critical failure combinations by analysis of models of the whole system (i.e. software, hardware, failure modes and environment). The advantage of these methods compared to traditional…

Logic in Computer Science · Computer Science 2010-06-29 Matthias Güdemann , Frank Ortmeier

Large Language Models (LLMs) have advanced Automated Heuristic Design (AHD) in combinatorial optimization (CO) in the past few years. However, existing discovery pipelines often require extensive manual trial-and-error or reliance on domain…

Neural and Evolutionary Computing · Computer Science 2026-02-19 Mingxin Yu , Ruixiao Yang , Chuchu Fan

Learned optimizers are a crucial component of meta-learning. Recent advancements in scalable learned optimizers have demonstrated their superior performance over hand-designed optimizers in various tasks. However, certain characteristics of…

Machine Learning · Computer Science 2023-06-01 Gaole Dai , Wei Wu , Ziyu Wang , Jie Fu , Shanghang Zhang , Tiejun Huang

We consider the adaptive control problem for discrete-time, nonlinear stochastic systems with linearly parameterised uncertainty. Assuming access to a parameterised family of controllers that can stabilise the system in a bounded set within…

Systems and Control · Electrical Eng. & Systems 2025-11-24 Seth Siriya , Jingge Zhu , Dragan Nešić , Ye Pu

Establishing a low-dimensional representation of the data leads to efficient data learning strategies. In many cases, the reduced dimension needs to be explicitly stated and estimated from the data. We explore the estimation of dimension in…

Methodology · Statistics 2022-02-10 Wei Q. Deng , Radu V. Craiu

The ubiquitous use of machine learning algorithms brings new challenges to traditional database problems such as incremental view update. Much effort is being put in better understanding and debugging machine learning models, as well as in…

Machine Learning · Computer Science 2020-02-28 Yinjun Wu , Val Tannen , Susan B. Davidson

We consider embedding a predictive machine-learning model within a prescriptive optimization problem. In this setting, called constraint learning, we study the concept of a validity domain, i.e., a constraint added to the feasible set,…

Optimization and Control · Mathematics 2025-05-30 Yilin Zhu , Samuel Burer

A recently developed measure-theoretic framework solves a stochastic inverse problem (SIP) for models where uncertainties in model output data are predominantly due to aleatoric (i.e., irreducible) uncertainties in model inputs (i.e.,…

Numerical Analysis · Mathematics 2023-02-15 Michael Pilosov , Carlos del-Castillo-Negrete , Tian Yu Yen , Troy Butler , Clint Dawson

Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in general online settings, when combined with world model and…

Machine Learning · Computer Science 2026-01-29 Florent Delgrange , Raphael Avalos , Willem Röpke

Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through downstream adaptation. We test this…

Computers and Society · Computer Science 2026-04-29 Emaan Bilal Khan , Amy Winecoff , Miranda Bogen , Dylan Hadfield-Menell

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

Machine Learning · Computer Science 2024-10-31 Philip Sosnin , Mark N. Müller , Maximilian Baader , Calvin Tsay , Matthew Wicker

Safe deployment of autonomous robots in diverse scenarios requires agents that are capable of efficiently adapting to new environments while satisfying constraints. In this work, we propose a practical and theoretically-justified approach…

Robotics · Computer Science 2022-02-17 Thomas Lew , Apoorva Sharma , James Harrison , Andrew Bylard , Marco Pavone

Unseen shifts in environment dynamics, driven by hidden parameters such as friction or gravity, create a challenge for maintaining safety. We address this challenge by proposing Adaptive Shielding, a framework for safe reinforcement…

Machine Learning · Computer Science 2026-02-03 Minjae Kwon , Tyler Ingebrand , Ufuk Topcu , Lu Feng

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns…

Machine Learning · Computer Science 2021-10-26 Korawat Tanwisuth , Xinjie Fan , Huangjie Zheng , Shujian Zhang , Hao Zhang , Bo Chen , Mingyuan Zhou

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning…

Machine Learning · Computer Science 2024-11-19 Junlin Wu , Huan Zhang , Yevgeniy Vorobeychik