paper-with-me

Papers

BaB-prob: Branch and Bound with Preactivation Splitting for Probabilistic Verification of Neural Networks

2025-09-30 · Fangji Wang, Panagiotis Tsiotras arxiv

Branch-and-bound with preactivation splitting has been shown highly effective for deterministic verification of neural networks. In this paper, we extend this framework to the probabilistic setting. We propose BaB-prob that iteratively divides the original problem into subproblems by splitting preactivations and leverages linear bounds computed by linear bound propagation to bound the probability for each subproblem. We prove soundness and completeness of BaB-prob for feedforward-ReLU neural networks. Furthermore, we introduce the notion of uncertainty level and design two efficient strategies for preactivation splitting, yielding BaB-prob-ordered and BaB+BaBSR-prob. We evaluate BaB-prob on untrained networks, MNIST and CIFAR-10 models, respectively, and VNN-COMP 2025 benchmarks. Across these settings, our approach consistently outperforms state-of-the-art approaches in medium- to high-dimensional input problems.

📄 PDF Abstract BibTeX arXiv:2509.25647

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Probabilistic Verification of Neural Networks using Branch and Bound

2024-05-27 · David Boetius, Stefan Leue, Tobias Sutter

Probabilistic verification of neural networks is concerned with formally analysing the output distribution of a neural network under a probability distribution of the inputs. Examples of probabilistic verification includ…

Fairness

TreeDQN: Learning to minimize Branch-and-Bound tree

2023-06-09 · Dmitry Sorokin, Alexander Kostin

Combinatorial optimization problems require an exhaustive search to find the optimal solution. A convenient approach to solving combinatorial optimization tasks in the form of Mixed Integer Linear Programs is Branch-and-…

Combinatorial Optimizationreinforcement-learningReinforcement LearningVariable Selection

Optimized Symbolic Interval Propagation for Neural Network Verification

2022-12-15 · Philipp Kern, Marko Kleine Büning, Carsten Sinz

Neural networks are increasingly applied in safety critical domains, their verification thus is gaining importance. A large class of recent algorithms for proving input-output relations of feed-forward neural networks ar…

Collision Avoidance

Bilateral Network with Channel Splitting Network and Transformer for Thermal Image Super-Resolution

2022-06-24 · Bo Yan, Leilei Cao, Fengliang Qi, Hongbin Wang

In recent years, the Thermal Image Super-Resolution (TISR) problem has become an attractive research topic. TISR would been used in a wide range of fields, including military, medical, agricultural and animal ecology. Du…

Image Super-ResolutionSSIMSuper-Resolution

Branch and Bound for Relational Verification of Neural Networks

2026-08-13 · Kota Fukuda, Zhenya Zhang, Guanqin Zhang, Jianjun Zhao arxiv

Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components.…