Abstract Safe controller synthesis with formal guarantees is widely employed in safety-critical systems. However, existing controller synthesis methods are subject to significant limitations in scalability and efficiency. This paper presents a novel controller incremental synthesis framework guided by barrier certificates (BCs), thereby generating a safe controller with BC verification. To enhance verification efficiency, we construct a learning-enabled polynomial BC combined with efficient post-verification, which is transformed into smaller-scale linear Programming (LP) subproblems for feasibility determination. Furthermore, we have implemented a tool called ISafeC and evaluated its performance over a set of benchmark examples. The comparative experimental results demonstrate the effectiveness and efficiency of our approach.

Safe controller synthesis is crucial for safety-critical applications. This paper presents a novel reinforcement learning approach to synthesize safe controllers for NN-controlled systems. The core idea leverages an iterative scheme that combines controller learning with neural barrier certificate (BC) verification, ultimately producing a provably safe deep neural network (DNN) controller with formal safety guarantees. The process begins by pre-training a well-performing DNN controller as an “oracle” via deep reinforcement learning (DRL). To formally verify the safety properties of the closed-loop system under the base controller, we devise a formal verification procedure that approximates the DNN controller using polynomial inclusion, followed by synthesizing neural BCs via sum-of-squares (SOS) relaxation. In cases where the base controller is insufficient to yield a real BC, the current spurious BC is incorporated as an additional penalty term to reshape the RL reward function, guiding the iterative refinement for new controllers. We implement an automated tool, NBCRL, and experimental results demonstrate the benefits of our method in terms of efficiency and scalability even for a nonlinear system with dimension up to 12.

Polynomial Lyapunov function $\mathcal{V}({\mathbf{x}})$ provides mathematically rigorous that converts stability analysis into efficiently solvable optimization problem. Traditional numerical methods rely on user-defined templates, while emerging neural $\mathcal{V}({\mathbf{x}})$ offer flexibility but exhibit poor generalization yield from naive Square NNs. In this paper, we propose a novel learning-enabled polynomial $\mathcal{V}({\mathbf{x}})$ synthesis approach, where an automated machine learning process guided by goal-oriented sampling to fit candidate $\mathcal{V}({\mathbf{x}})$ which naturally compatible with the sum-of-squares (SOS) soundness verification. The framework is structured as an iterative loop between a Learner and a Verifier, where the Learner trains expressive polynomial $\mathcal{V}({\mathbf{x}})$ network via polynomial expansions, while the Verifier encodes learned candidates with SOS constraints to identify a real $\mathcal{V}({\mathbf{x}})$ by solving LMI feasibility test problems. The entire procedure is driven by a high-accuracy counterexample guidance technique to further enhance efficiency. Experimental results demonstrate that our approach outperforms both SMT-based polynomial neural Lyapunov function synthesis and traditional SOS method.

The design of controllers for safety-critical systems is an important research issue. Especially, the generation of controllers with formal safety guarantees is a challenging problem. Recently, for safety objectives of various system control tasks, machine learning technologies have been used to achieve ideal training and simulation performance, but formal guarantees are still lacking. This paper takes advantages of learning technology to assist safe controller synthesis with formal guarantees. On the one hand, the generation of verifiable safe controllers is aided by reinforcement learning; on the other hand, a set of barrier certificates (BC), i.e. a vector BC, is synthesized with the aid of deep learning to certify the safety of synthesized controllers. Vector BCs are more expressive than the conventional single BCs for safety verification. Compared with the existing work on vector BC generation, our method has two advantages: first, our method verifies a learned candidate vector BC, rather than directly generating a verified one, and thus has low computational complexity; second, the existing method has made relaxations to the non-convex vector BC constraints, which reduced the feasible region of solutions, while our method can deal with the original constraints. Furthermore, experiments fully demonstrate the effectiveness of our method on a series of benchmarks.

Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.

There is a pressing need to ensure the safety of closed-loop systems with neural network controllers, as they are often incorporated into safety-critical applications. To address this issue, we propose a novel approach for generating barrier certificates, which combines counterexample-guided learning with efficient Sum-Of-Squares (SOS) based verification. By leveraging barrier certificate candidates obtained from the learning phase, our proposed method offers an efficient verification procedure that solves three Linear Matrix Inequality (LMI) constraint feasibility testing problems, instead of relying on an SMT solver to verify the barrier certificate conditions. We conduct comparison experiments on a set of benchmarks, demonstrating the advantages of our method in terms of efficiency and scalability, which enable effective verification of high-dimensional systems.

Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy.Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance.However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models.In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zeroshot TTS models.To simulate real-world scenarios, we employ diverse attack methods and audio prompts from different datasets.Experiments show that, through novel attackaugmented training, the Wav2Vec2-large and Whisper-medium models achieve equal error rates of 4.1% and 6.5% respectively.Additionally, we demonstrate our models' outstanding few-shot ADD ability by fine-tuning with just one minute of target-domain data.Nonetheless, neural codec compressors greatly affect the detection accuracy, necessitating further research.Our dataset is publicly available 1 .

The recognition of rare named entities, such as personal names and terminologies, is challenging for automatic speech recognition (ASR) systems, especially when they are not frequently observed in the training data.In this paper, we introduce keyword spotting enhanced Whisper (KWS-Whisper), a novel ASR system that leverages the Whisper model and performs openvocabulary keyword spotting (OV-KWS) on the hidden states of the Whisper encoder to recognize user-defined named entities.These entities serve as prompts for the Whisper decoder.To optimize the model, we propose a multitask training approach that learns OV-KWS and contextual-ASR tasks.We evaluate our approach on Chinese Aishell hot word subsets and two internal code-switching test sets and show that it significantly improves the entity recall compared to the original Whisper model.Moreover, we demonstrate that the OV-KWS can be a plug-andplay module to enhance the ASR error correction methods and frozen Whisper models.