Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high false-positive rates. This not only reduces detection efficiency but also significantly increases the manual screening burden on developers. Recent advances in large language models (LLMs) and multi-agent collaborative architectures have demonstrated remarkable potential for tackling complex tasks, offering a novel technological perspective for sensitive information detection. In response to these challenges, we propose Argus, a multi-agent collaborative framework for detecting sensitive information. Argus employs a three-tier detection mechanism that integrates key content, file context, and project reference relationships to effectively reduce false positives and enhance overall detection accuracy. To comprehensively evaluate Argus in real-world repository environments, we developed two new benchmarks, one to assess genuine leak detection capabilities and another to evaluate false-positive filtering performance. Experimental results show that Argus achieves up to 94.86% accuracy in leak detection, with a precision of 96.36%, recall of 94.64%, and an F1 score of 0.955. Moreover, the analysis of 97 real repositories incurred a total cost of only 2.2$. All code implementations and related datasets are publicly available at https://github.com/TheBinKing/Argus-Guard for further research and application.

--Advancements in foundation models have made it possible to conduct applications in various downstream tasks. Especially, the new era has witnessed a remarkable capability to extend Large Language Models (LLMs) for tackling tasks of 3D scene understanding. Current methods rely heavily on 3D point clouds, but the 3D point cloud reconstruction of an indoor scene often results in information loss. Some textureless planes or repetitive patterns are prone to omission and manifest as voids within the reconstructed 3D point clouds. Besides, objects with complex structures tend to introduce distortion of details caused by misalignments between the captured images and the dense reconstructed point clouds. Based on these insights, we propose Argus, a novel 3D multimodal framework that leverages multi-view images for enhanced 3D scene understanding with LLMs. In general, Argus can be treated as a 3D Large Multimodal Foundation Model (3D-LMM) since it takes various modalities as input(text instructions, 2D multi-view images, and 3D point clouds) and expands the capability of LLMs to tackle 3D tasks. Argus involves fusing and integrating multi-view images and camera poses into view-as-scene features, which interact with the 3D features to create comprehensive and detailed 3D-aware scene embeddings. Our approach compensates for the information loss while reconstructing 3D point clouds and helps LLMs better understand the 3D world. Extensive experiments demonstrate that our method outperforms existing 3D-LMMs in various downstream tasks. NTRODUCTION Received 8 August 2024; revised 23 March 2025; accepted 12 June 2025. Yifan Xu is with School of Computer Science and Engineering, Bei-hang University, Beijing 100191, China, also with Beijing Digital Native Digital City Research Center, Beijing 100084, China (email: xudax-ian2001@gmail.com).

Large Language Model-based Multi-Agent Systems (MASs) have demonstrated strong advantages in addressing complex real-world tasks. However, due to the introduction of additional attack surfaces, MASs are particularly vulnerable to misinformation injection. To facilitate a deeper understanding of misinformation propagation dynamics within these systems, we introduce MisinfoTask, a novel dataset featuring complex, realistic tasks designed to evaluate MAS robustness against such threats. Building upon this, we propose ARGUS, a two-stage, training-free defense framework leveraging goal-aware reasoning for precise misinformation rectification within information flows. Our experiments demonstrate that in challenging misinformation scenarios, ARGUS exhibits significant efficacy across various injection attacks, achieving an average reduction in misinformation toxicity of approximately 28.17% and improving task success rates under attack by approximately 10.33%. Our code and dataset is available at: https://github.com/zhrli324/ARGUS.

The space-air-ground integrated network (SAGIN) has recently emerged as a core element in the 6G networks. However, traditional centralized and synchronous optimization algorithms are unsuitable for SAGIN due to infrastructureless and time-varying environments. This paper aims to develop a novel Asynchronous algorithm a.k.a. Argus for tackling non-convex and non-smooth decentralized federated bilevel learning over SAGIN. The proposed algorithm allows networked agents (e.g. autonomous aerial vehicles) to tackle bilevel learning problems in time-varying networks asynchronously, thereby averting stragglers from impeding the overall training speed. We provide a theoretical analysis of the iteration complexity, communication complexity, and computational complexity of Argus. Its effectiveness is further demonstrated through numerical experiments.

Network Intrusion Detection Systems (NIDS) are vital for ensuring enterprise security. Recently, Graph-based NIDS (GIDS) have attracted considerable attention because of their capability to effectively capture the complex relationships within the graph structures of data communications. Despite their promise, the reproducibility and replicability of these GIDS remain largely unexplored, posing challenges for developing reliable and robust detection systems. This study bridges this gap by designing a systematic approach to evaluate state-of-the-art GIDS, which includes critically assessing, extending, and clarifying the findings of these systems. We further assess the robustness of GIDS under adversarial attacks. Evaluations were conducted on three public datasets as well as a newly collected large-scale enterprise dataset. Our findings reveal significant performance discrepancies, highlighting challenges related to dataset scale, model inputs, and implementation settings. We demonstrate difficulties in reproducing and replicating results, particularly concerning false positive rates and robustness against adversarial attacks. This work provides valuable insights and recommendations for future research, emphasizing the importance of rigorous reproduction and replication studies in developing robust and generalizable GIDS solutions.

IoT application domains, device diversity and connectivity are rapidly growing. IoT devices control various functions in smart homes and buildings, smart cities, and smart factories, making these devices an attractive target for attackers. On the other hand, the large variability of different application scenarios and inherent heterogeneity of devices make it very challenging to reliably detect abnormal IoT device behaviors and distinguish these from benign behaviors. Existing approaches for detecting attacks are mostly limited to attacks directly compromising individual IoT devices, or, require predefined detection policies. They cannot detect attacks that utilize the control plane of the IoT system to trigger actions in an unintended/malicious context, e.g., opening a smart lock while the smart home residents are absent. In this paper, we tackle this problem and propose ARGUS, the first self-learning intrusion detection system for detecting contextual attacks on IoT environments, in which the attacker maliciously invokes IoT device actions to reach its goals. ARGUS monitors the contextual setting based on the state and actions of IoT devices in the environment. An unsupervised Deep Neural Network (DNN) is used for modeling the typical contextual device behavior and detecting actions taking place in abnormal contextual settings. This unsupervised approach ensures that ARGUS is not restricted to detecting previously known attacks but is also able to detect new attacks. We evaluated ARGUS on heterogeneous real-world smart-home settings and achieve at least an F1-Score of 99.64% for each setup, with a false positive rate (FPR) of at most 0.03%.

The recent growth of the overall NFT market has created big challenges for development teams trying to scale market infrastructure. And as NFT trading volume has increased dramatically, so has the incentive for bad actors to sell plagiarized art and counterfeit NFTs. At the same time, the need to verify the legitimacy of NFT collections has created problems for many NFT creators. Since it takes marketplaces just as much effort (if not more) to verify a small collection as a large one, marketplaces are incentivized to put off verifying smaller collections in favor of larger ones that generate more revenue. And for creators of smaller NFT collections, this incentive frequently leads to lengthy delays in gaining visibility on leading marketplaces. Even in relatively small NFT ecosystems, current verification methods create market bottlenecks that are bad for creators, marketplaces and collectors.

CADe & CAPs technology based on artificial intelligence algorithms can assist endoscopists in detecting colorectal neoplasia and sizing abnormalities. Argus is vendor-neutral technology by integrating with existing ERWs/EHRs, scopes and processors to create the least amount of workflow changes for clinicians. Argus is launched during the procedure to assist with the detection and sizing of abnormalities utilizing artificial intelligence and machine learning. Argus simultaneously captures the highest quality images and video from the processor to aid in the decision making using CADe (computer-aided detection) and CAPs (computer-aided sizing) for the clinician to determine a treatment plan and generate reports. Utilizing Argus during a colonoscopy can increase Adenoma Detection Rates (ADRs) and improve patient recall times.

Reolink's Argus cameras have ably filled the need for an essentials-only wireless security camera. The Argus 2E is the latest in the family, but where it sits in the lineage is a little confusing. Given its name, you'd be forgiven for thinking it's an update on the Argus 2, but that model evolved into the completely redesigned Argus 3, The 2E actually replaces the Argus Pro, which, contrary to its name was not a premium version of the Argus, and even lacked a few of the main model's features. It makes sense, then, that the 2E doesn't sport the new design of the Argus 3 but looks like a slightly modified version of the Argus Pro. Most of the specs are the same, too: 1080p video, two-way audio, and passive infrared motion detection. And like the Argus Pro, the 2E is powered by a 5200mAh rechargeable battery that can be continually charged with an optional solar panel ($25) should you deploy this indoor/outdoor camera outside.

Experts in ethics, privacy and bias in AI spoke at the AI Expo Africa conference held in Cape Town this week. Highlights included an AI art and music challenge, and French company Rhoban who showed off their soccer-playing robots. The robots are also the RoboWorld Cup champions. Mushambi Mutuma, chief executive at tech company Altivex said AI was controlled by the people who input the data. "Last year Google's facial recognition software kept inputting African-Americans as gorillas. We have to have new voices and a bit more diversity because the data will never come back accurate and that's what we've tried to solve from bias," he said.