arXiv AI June 3, 2026 By Ido Shmuel, Guy Katz

Neural Network Verification using Partial Multi-Neuron Relaxation

arXiv:2605. 30155v3 Announce Type: replace-cross Abstract: The increasing integration of deep neural networks in critical systems has spawned a theoretical and practical interest in formally guaranteeing safety properties about their behavior.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

safety

arXiv Machine Learning

Jun 19

Shifting-based Optimizable Linear Relaxations for General Activation Functions

arXiv:2606. 20292v1 Announce Type: new Abstract: The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains.

By Philipp Kern, L\'aszl\'o Antal, Erika \'Abr\'aham, Carsten Sinz

benchmarks safety

arXiv Machine Learning

Aug 26

$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks

arXiv:2608.24743v1 Announce Type: new Abstract: Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-...

By Hanna Jiamei Zhang, Alan Papalia, Michael Everett, David M. Rosen

agents safety

Hugging Face Trending Papers

Aug 25

$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks

Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant...

agents safety

arXiv Machine Learning

Aug 4

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

arXiv:2602. 06737v2 Announce Type: replace Abstract: We present a generalized framework for the range verification of neural networks featuring non-linear activation functions.

By Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan, Ramneet Kaur, Tuhin Sahai, Susmit Jha

benchmarks

Hugging Face Trending Papers

Aug 13

Branch and Bound for Relational Verification of Neural Networks

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. Compared to simple trace properties (e.

safety

arXiv Machine Learning

Aug 14

Branch and Bound for Relational Verification of Neural Networks

arXiv:2608. 13118v1 Announce Type: new Abstract: 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.

By Kota Fukuda, Zhenya Zhang, Guanqin Zhang, Jianjun Zhao

safety

One email a morning, machine-written

Related stories

Shifting-based Optimizable Linear Relaxations for General Activation Functions

$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks

$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

Branch and Bound for Relational Verification of Neural Networks

Branch and Bound for Relational Verification of Neural Networks