Adversarial examples have become a critical focus in ensuring the security and robustness of deep learning (DL) systems. In this paper, we introduce an innovative approach for generating adversarial examples, designed to identify and diagnose common errors in DL models. Specifically, our method targets two key issues: Oscillating Loss (OL) and Slow Convergence (SC), providing valuable insight into model performance and fault detection. Using a reinforcement learning framework, we generate test data that effectively distinguishes between models with and without these errors. We consider the MNIST and CIFAR-10 datasets and test our approach on neural networks with various architectures, demonstrating significant improvements in error detection across different types of models. These results highlight the substantial effectiveness of our proposed method in improving the reliability of DL models. Furthermore, we demonstrate the scalability of our approach, showing that it can be used to diagnose various common errors in DL models with minimal modifications.

The wide deployment of Deep Neural Networks (DNNs), though achieving great success in many domains, has severe safety concerns. Inspired by testing criteria from traditional software engineering, various coverage criteria have been proposed to ensure the safety of DNNs. However, the validity of coverage criteria was questioned in related researches. In this paper, we evaluate the performance of dominating coverage criteria in two aspects: 1) distinguishing different qualities of test sets, 2) improving the safety and robustness of DNNs. The evaluation result confirms that coverage criteria are meaningful metrics for DNNs. Specifically, the way for improving robustness is contrary to the previous assumption: the higher coverage criterion score, the better. In addition, we propose a new coverage criterion called Independence Neuron Coverage (INC) which is finer grained to capture DNNs' subtle behaviour. Experiments show that INC is efficient and performs better than other evaluated coverage criteria in both aspects.

The Nervos CKB (Common Knowledge Base) is a public permissionless blockchain designed for a peer-to-peer crypto-economy network.The CKB Consensus Protocol is a key part of the Nervos CKB blockchain that improves the Consensus's performance limit of Bitcoin.In this paper, we develop a formal model of the CKB Consensus Protocol and verify some important properties of the protocol using the UPPAAL model checker.Based on the formal model, the reliability of CKB Consensus Protocol can be guaranteed.

Deep Learning (DL) offers a data-driven programming paradigm in which Deep Neural Networks (DNNs) can be constructed through a set of training data.It has been widely adopted in many real-world applications.However, many studies have shown that DL systems suffer from adversarial attacks, especially when they are applied to security-and safetycritical domains.Given that formal verification has proved a great success in many areas such as software engineering, using it to achieve a high-level security assurance in DL systems is considered promising.In this paper, we design and implement DeepAuto which makes the significant bridge between automata and DNNs.With the aid of DeepAuto, we demonstrate how DNNs can be modeled as automata and be verified formally in the widely used model checker UPPAAL.The potential usefulness of DeepAuto shows the connection between DNNs and automata and provides a solution for the construction of more trustworthy DL systems.

IEEE 802.11i is the IEEE standard that provides enhanced MAC security and has been widely used in wireless networks and Internet of Things.It improves IEEE 802.11(1999) by providing a Robust Security Network (RSN) with two new protocols: the 4-way handshake and the Group-key handshake.These protocols utilize the authentication services and port access control described in IEEE 802.1X to establish and change the appropriate cryptographic keys.In this paper, we carry out a formal modeling and verification approach based on timed automata for IEEE 802.11i protocol, using the UPPAAL model checker, to check correctness of the changes in IEEE 802.11i protocol and provide better security.

IEEE 802.11i is the IEEE standard that provides enhanced MAC security and has been widely used in wireless networks and Internet of Things. It improves IEEE 802.11 (1999) by providing a Robust Security Network (RSN) with two new protocols: the Four-Way Handshake and the Group Key Handshake. These protocols utilize the authentication services and port access control described in IEEE 802.1X to establish and change the appropriate cryptographic keys. In this paper, we carry out a formal modeling and verification approach based on timed automata for IEEE 802.11i protocol, using the UPPAAL model checker, to check correctness of the changes in IEEE 802.11i protocol and provide better security.