Embodied Action Sequence Planning focuses on the capability of embodied agents to implement action planning via environmental perception.This technology enables diverse intelligent assistance for real-world scenarios such as home and office environments.To address the limitations of existing embodied agents in meeting the requirement for proactivity and achieving joint understanding of visual and audio information, this study investigates the ability of embodied agents to proactively provide assistance through action sequence planning based on joint understanding of vision and audio perception without explicit human instructions.Correspondingly, we propose PEAP, the first multimodal proactive embodied action sequence planning dataset.We evaluate the performance of multiple Large Language Models on the PEAP dataset.The results demonstrate that these models still exhibit significant deficiencies on this task particularly lacking accurate environmental perception capabilities.Furthermore, ablation experiment and replacement experiment further corroborate that the joint understanding of multimodal information can significantly improve the models' performance on proactive embodied action sequence planning task.Our dataset and code are publicly available 1 .

Machine Learning (ML) malware detectors rely heavily on crowd-sourced AntiVirus (AV) labels, with platforms like VirusTotal serving as trusted sources of malware annotations. But what if attackers could manipulate these labels to classify benign software as malicious? We introduce label spoofing attacks, a new threat that contaminates crowd-sourced datasets by embedding minimal and undetectable malicious patterns into benign samples. These patterns coerce AV engines into misclassifying legitimate files as harmful, enabling poisoning attacks against ML-based malware classifiers trained on those data. We demonstrate this scenario by developing AndroVenom, a methodology for polluting realistic data sources and launching subsequent poisoning attacks against ML malware detectors. Experiments show that not only are state-of-the-art feature extractors unable to filter such injections, but various ML models experience Denial-of-Service (DoS) with as little as 1% poisoned samples. Additionally, attackers can flip decisions for specific unaltered benign samples by modifying only 0.015% of the training data, threatening their reputation and market share, while evading anomaly detectors operating on the training data. We conclude by raising concerns about the trustworthiness of ML training processes based on AV annotations and argue that further investigation is needed to develop more reliable labeling strategies.

Speech entity linking amis to recognize mentions from speech and link them to entities in knowledge bases. Previous work on entity linking mainly focuses on visual context and text context. In contrast, speech entity linking focuses on audio context. In this paper, we first propose the speech entity linking task. To facilitate the study of this task, we propose the first speech entity linking dataset, TED-EL. Our corpus is a high-quality, human-annotated, audio, text, and mention-entity pair parallel dataset derived from Technology, Entertainment, Design (TED) talks and includes a wide range of entity types (24 types). Based on TED-EL, we designed two types of models: ranking-based and generative speech entity linking models. We conducted experiments on the TED-EL dataset for both types of models. The results show that the ranking-based models outperform the generative models, achieving an F1 score of 60.68%.

The extensive popularity of Android operating system hones the increased malware attacks and threatens the Android ecosystem. Machine learning is one of the versatile tools to detect legacy and new malware with high accuracy. However, these Machine Learning (ML) models are vulnerable to adversarial attacks, which severely threaten their cybersecurity deployment. To combat the deterrence of ML models against adversarial attacks, we propose a novel randomization method as a defense for image-based detection systems. In addition to defensive randomization, the paper also introduces a novel method, called AutoE, for transforming an APK to an image by leveraging API calls only. To evaluate the effectiveness of randomization as a defense against adversarial settings, we compare our AutoE with two state-of-the-art image-based Android malware detection systems. The experimental results reveal that the randomization is a strong defensive hood for image-based Android malware detection systems against adversarial attacks. Moreover, our novel AutoE detects malware with 96% accuracy and the randomization approach makes it harder against adversarial attacks.