Abstract Deep Reinforcement Learning (DRL) has demonstrated its strength in developing intelligent systems. These systems shall be formally guaranteed to be trustworthy when applied to safety-critical domains, which is typically achieved by formal verification performed after training. This train-then-verify process has two limits: (i) trained systems are difficult to formally verify due to their continuous and infinite state space and inexplicable AI components (i.e., deep neural networks), and (ii) the ex post facto detection of bugs increases both the time- and money-wise cost of training and deployment. In this paper, we propose a novel verification-in-the-loop training framework called Trainify for developing safe DRL systems driven by counterexample-guided abstraction and refinement. Specifically, Trainify trains a DRL system on a finite set of coarsely abstracted but efficiently verifiable state spaces. When verification fails, we refine the abstraction based on returned counterexamples and train again on the finer abstract states. The process is iterated until all predefined properties are verified against the trained system. We demonstrate the effectiveness of our framework on six classic control systems. The experimental results show that our framework yields more reliable DRL systems with provable guarantees without sacrificing system performance such as cumulative reward and robustness than conventional DRL approaches.

Formal robustness verification of deep neural networks (DNNs) is a promising approach for achieving a provable reliability guarantee to AI-enabled software systems. Limited scalability is one of the main obstacles to the verification problem. In this paper, we propose eager falsification to accelerate the robustness verification of DNNs. It divides the verification problem into a set of independent subproblems and solves them in descending order of their falsification probabilities. Once a subproblem is falsified, the verification terminates with a conclusion that the network is not robust. We introduce a notion of label affinity to measure the falsification probability and present an approach to computing the probability based on symbolic interval propagation. Our approach is orthogonal to existing verification techniques. We integrate it into four state-of-the-art verification tools, i.e., MIPVerify, Neurify, DeepZ, and DeepPoly, and conduct extensive experiments on 8 benchmark datasets. The experimental results show that our approach can significantly improve these tools by up to 200x speedup when the perturbation distance is in a reasonable range.

In social networking, the users' friends are dynamically distributed all over the world and served by many nontrusted and independent providers, thus it is hard to explicitly set-up their public keys with the conventional Public Key Infrastructure so as to provide secure social networking. The present paper aims to build transparently secure channels for social networking. It employs identity-based encryption schemes to enable secure communication with legacy social networking applications based on the users' identities such as telephone numbers. In other words, by stealthily injecting the identity-based security function into the existing social networking applications, a user can securely send the messages with the (insecure) applications. The experiments on the instant communication with Android smartphones demonstrate its effectiveness and efficiency.