相关论文: SEBA: Sample-Efficient Black-Box Attacks on Visual…

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside the training environment. Existing evaluations, including the original ACT and SmolVLA…

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become…

One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on…

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust…

The adversarial attack can force a CNN-based model to produce an incorrect output by craftily manipulating human-imperceptible input. Exploring such perturbations can help us gain a deeper understanding of the vulnerability of neural…

Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract…

Survival analysis (SA) models have been widely studied in mining electronic health records (EHRs), particularly in forecasting the risk of critical conditions for prioritizing high-risk patients. However, their vulnerability to adversarial…

Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have mainly focused on static scenes; however, it remains unclear…

Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…

Deep Neural Networks can be easily fooled by small and imperceptible perturbations. The query-based black-box attack (QBBA) is able to create the perturbations using model output probabilities of image queries requiring no access to the…

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…

Federated learning learns a neural network model by aggregating the knowledge from a group of distributed clients under the privacy-preserving constraint. In this work, we show that this paradigm might inherit the adversarial vulnerability…

Deep learning models are vulnerable to external attacks. In this paper, we propose a Reinforcement Learning (RL) based approach to generate adversarial examples for the pre-trained (target) models. We assume a semi black-box setting where…

Due to the broad range of applications of reinforcement learning (RL), understanding the effects of adversarial attacks against RL model is essential for the safe applications of this model. Prior theoretical works on adversarial attacks…

Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches. However, both global perturbations and local patches…

This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target…

Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledge of the domain or task is unavailable, training RL agents…

Meta reinforcement learning (RL) attempts to discover new RL algorithms automatically from environment interaction. In so-called black-box approaches, the policy and the learning algorithm are jointly represented by a single neural network.…