We present a novel semidefinite programming (SDP) relaxation that enables tight and
efficient verification of neural networks. The tightness is achieved by combining SDP …

We propose an enhanced semidefinite program (SDP) relaxation to enable the tight and
efficient verification of neural networks (NNs). The tightness improvement is achieved by …

This paper outlines some of the key methods we developed towards the formal verification of
multiagent systems, covering both symbolic and connectionist systems. It discusses logic …

Neural networks are widely used in various applications such as image classification,
speech recognition and natural language processing. As intelligent systems often rely on …

We introduce a novel method based on semidefinite program (SDP) for the tight and efficient
verification of neural networks. The proposed SDP relaxation advances the present state of …

Neural networks have demonstrated great success in modern machine learning systems.
However, they remain susceptible to incorrect corner-case behaviors, often behaving …

The evaluation and verification of neural networks (NNs), as a part of their safe design and
deployment, becomes a hot research topic, particularly with the recent studies showing their …