Strong adversarial examples are crucial for evaluating and enhancing the robustness of deep neural networks. However, the performance of popular attacks is usually sensitive, for instance, to minor image transformations, stemming from limited information ─ typically only one input example, a handful of white-box source models, and undefined defense strategies. Hence, the crafted adversarial examples are prone to overfit the source model, which hampers their transferability to unknown architectures. In this paper, we propose an approach named Multiple Asymptotically Normal Distribution Attacks (MultiANDA) which explicitly characterize adversarial perturbations from a learned distribution. Specifically, we approximate the posterior distribution over the perturbations by taking advantage of the asymptotic normality property of stochastic gradient ascent (SGA), then employ the deep ensemble strategy as an effective proxy for Bayesian marginalization in this process, aiming to estimate a mixture of Gaussians that facilitates a more thorough exploration of the potential optimization space. The approximated posterior essentially describes the stationary distribution of SGA iterations, which captures the geometric information around the local optimum. Thus, MultiANDA allows drawing an unlimited number of adversarial perturbations for each input and reliably maintains the transferability. Our proposed method outperforms ten state-of-the-art black-box attacks on deep learning models with or without defenses through extensive experiments on seven normally trained and seven defense models.

Abstract The safety and robustness of deep neural networks (DNNs) are currently of great concern. Adequate testing is commonly an effective technique to ensure the software's trustworthiness. However, existing DNN testing methods generate many invalid test inputs, which inevitably brings increased computational overhead and reduces the efficiency of DNN testing. In this paper, we focus on testing task‐specific DNN and investigating diverse, valid and natural test input generation based on data augmentation techniques. Specifically, we propose AugTest, a DNN testing method based on stochastic optimization with momentum, searching for optimal compositions of data augmentation parameters to efficiently generate diverse and valid test inputs. Experimental results show that our proposed method can effectively explore the data manifold space and find valid test inputs with high diversity and naturalness. Compared with the best‐performing baseline, AugTest can generate more test inputs with more average diversity and less average time. Furthermore, the generated test inputs have competitive generalizability to DNNs with different structures. The test error rates exceed 70% when testing other DNN models performing similar tasks using the test inputs generated by AugTest. This implies that our method can produce more valid and generalized data to unveil DNNs' errors.

ABSTRACT Despite numerous applications of deep learning technologies on critical tasks in various domains, advanced deep neural networks (DNNs) face persistent safety and security challenges, such as the overconfidence in predicting out‐of‐distribution samples and susceptibility to adversarial examples. Thorough testing by exploring the input space serves as a key strategy to ensure their robustness and trustworthiness of these networks. However, existing testing methods focus on disclosing more erroneous model behaviours, overlooking the validity of the generated test inputs. To mitigate this issue, we investigate devising valid test input generation method for DNNs from a predictive uncertainty perspective. Through a large‐scale empirical study across 11 predictive uncertainty metrics for DNNs, we explore the correlation between validity and uncertainty of test inputs. Our findings reveal that the predictive entropy‐based and ensemble‐based uncertainty metrics effectively characterize the input validity demonstration. Building on these insights, we introduce UCTest, an uncertainty‐guided deep learning testing approach, to efficiently generate valid and authentic test inputs. We formulate a joint optimization objective: to uncover the model's misbehaviours by maximizing the loss function and concurrently generate valid test input by minimizing uncertainty. Extensive experiments demonstrate that our approach outperforms the current testing methods in generating valid test inputs. Furthermore, incorporating natural variation through data augmentation techniques into UCTest effectively boosts the diversity of generated test inputs.

A timely and complete test is an important factor to assure the functionality and safety of a railway signal system before it is put into service. With the development of rail transportation in China, the traditional semiautomatic test methods cannot satisfy the timely and complete test requirements any longer. This paper proposes an automated model-based test method. First, colored Petri nets are used as a formal language to describe the system specification. Second, the all paths covered optimal algorithm and the sequence priority selected algorithm are proposed to generate the test cases and sequences automatically. Third, taking a typical radio block center (RBC) handover scenario as an example, the generated test cases and sequences are applied into the RBC functionality test platform. The testing result validated the feasibility and efficiency of the proposed automated test method. Compared with the random-walk-based test sequence generation algorithm, the repeatability rate of the generated test sequences is reduced by 46%. The test sequences can cover all the generated test cases, and the cases can cover all the related criteria in the function requirements specification of the Chinese Train Control System Level 3.