Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which
aims to trigger misbehavior of neural network models under attacker-controlled conditions …

Patch robustness certification is an emerging kind of defense technique against adversarial
patch attacks with provable guarantees. There are two research lines: certified recovery and …

In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL)
models, many state-of-the-art robustness-oriented fuzzing techniques are metric-oriented …

Large language models (LLMs) enhanced by retrieval-augmented generation (RAG)
provide effective solutions in various application scenarios. However, developers face …

Patch robustness certification ensures no patch within a given bound on a sample can
manipulate a deep learning model to predict a different label. However, existing techniques …

While Large Language Models (LLMs) have seen widespread applications across
numerous fields, their limited interpretability poses concerns regarding their safe operations …

Nowadays there is growing demand for surveillance applications due to the safety and
security from anomalous events. An anomaly in the video is referred to as an event that has …

The use of transformers for vision tasks has challenged the traditional dominant role of
convolutional neural networks (CNN) in computer vision (CV). For image classification tasks …

Benefiting from the advancements in LLMs, NLP software has undergone rapid
development. Such software is widely employed in various safety-critical tasks, such as …

In recent years, machine learning systems have been developed that demonstrate
remarkable performance on many tasks. However, naive metrics of performance, such as …