arXiv:2611.17883v1 Announce Type: new Abstract: Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by pr…
⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5331, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.13196v1 Announce Type: new Abstract: LLM-based agents can reason, use tools and collaborate. However, coordinating increasingly complex agentic applications becomes difficult to understand, monitor and improve. Decisions distributed across prompts, tool calls and appl…
arXiv:2611.10612v1 Announce Type: new Abstract: As enterprise systems grow in scale and complexity, manual log analysis and conventional SIEM tools struggle to keep pace with the volume and diversity of incidents. To address this challenge, this paper proposed a multi-agent AI f…
8.0.0, 8.0.0, 8.0.0, 17.14.0, 18.11.0, 18.12.0
ASP.NET Core có thuật toán kém hiệu quả, cho phép kẻ tấn công không xác thực gây từ chối dịch vụ (DoS) qua mạng. Đây là lỗ hổng mới được ghi nhận trong năm 2026, cần cập nhật vá lỗi nhanh chóng.
🎯 Kẻ tấn công làm gì (từng bước)
- Gửi dữ liệu gây crash hoặc tiêu tốn tài nguyên
- Dịch vụ ngừng phục vụ
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Dịch vụ restart liên tục, RAM/CPU tăng vọt
- Nhiều request cùng một tham số từ ít IP
🛡 Phòng ngay (làm được hôm nay)
- Vá/cập nhật
- Giới hạn tần suất + giới hạn kích thước request
- Có giám sát uptime và tự khởi động lại
arXiv:2611.13161v1 Announce Type: new Abstract: Effective search and rescue (SAR) operations require autonomous systems capable of coordinating multiple heterogeneous agents, adapting to dynamic hazards, and aligning with human mission intent. Existing language-guided reinforcem…
arXiv:2611.10026v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility cou…
arXiv:2611.10723v1 Announce Type: new Abstract: Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defens…
11.0.0-preview.1, 11.0.0-preview.1, 11.0.0-preview.1, NOT_YET_AVAILABLE
Inefficient algorithmic complexity in .NET allows an unauthorized attacker to deny service over a network.
🎯 Kẻ tấn công làm gì (từng bước)
- Gửi dữ liệu gây crash hoặc tiêu tốn tài nguyên
- Dịch vụ ngừng phục vụ
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Dịch vụ restart liên tục, RAM/CPU tăng vọt
- Nhiều request cùng một tham số từ ít IP
🛡 Phòng ngay (làm được hôm nay)
- Vá/cập nhật
- Giới hạn tần suất + giới hạn kích thước request
- Có giám sát uptime và tự khởi động lại
<= v2.17.0
Lỗ hổng tiết lộ thông tin nhạy cảm trong SAP Cloud SDK cho AI (Node.js) khi thông tin đăng nhập vô tình xuất hiện trong tin nhắn lỗi. Mặc dù yêu cầu điều kiện phức tạp để khai thác, đây vẫn là một lỗ hổng bảo mật quan trọng cần lưu ý cho các ứng dụng sử dụng SDK này.
🎯 Kẻ tấn công làm gì (từng bước)
- Khai thác endpoint trả về quá nhiều (stack trace, danh sách user, phiên bản)
- Thu thập thông tin để chọn đòn tấn công tiếp
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Response chứa stack trace, đường dẫn nội bộ, phiên bản phần mềm
- Dò hàng loạt đường dẫn (.git, .env, backup)
🛡 Phòng ngay (làm được hôm nay)
- Tắt hiển thị lỗi ra ngoài (debug=false)
- Chặn .git/.env/backup ở web server
- Vá thành phần bị lỗi
🧩 Chức năng: Công cụ quanh mô hình ngôn ngữ (prompt/agent)
Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, Min…
Researchers unpacked, mapped, and recreated complex software and the Turla malware, raising fresh concerns for defenders.
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with bot…
arXiv:2611.17814v1 Announce Type: new Abstract: With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product catego…
arXiv:2611.17596v1 Announce Type: new Abstract: Evaluating tight Differential Privacy (DP) parameters for DP matrix factorization with privacy amplification by sampling requires analyzing high-dimensional, correlated Gaussian mixtures. Because integrating these mixture distribut…
arXiv:2611.18563v1 Announce Type: cross Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification Syste…
3.2.0
Eclipse Langium (phiên bản 3.2.0 đến 4.4.0) gặp lỗi độ phức tạp thuật toán (CWE-407) trong IndentationAwareTokenBuilder. Kẻ tấn công có thể tạo tài liệu có cấu trúc thụt lề đặc biệt để làm nghẽn Node.js event loop, gây ra tấn công từ chối dịch vụ (DoS).
🎯 Kẻ tấn công làm gì (từng bước)
- Gửi dữ liệu gây crash hoặc tiêu tốn tài nguyên
- Dịch vụ ngừng phục vụ
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Dịch vụ restart liên tục, RAM/CPU tăng vọt
- Nhiều request cùng một tham số từ ít IP
🛡 Phòng ngay (làm được hôm nay)
- Vá/cập nhật
- Giới hạn tần suất + giới hạn kích thước request
- Có giám sát uptime và tự khởi động lại
arXiv:2611.12934v1 Announce Type: new Abstract: While multimodal agents now carry out complex data analysis with tools, their ability to turn decades of satellite imagery into reliable land-change analysis, crucial for Earth observation science, remains unmeasured. Existing benc…
arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …
Red Hat has announced the general availability of Red Hat OpenShift 5, bringing built-in operational intelligence, zero trust security and a longer, predictable lifecycle to the hybrid cloud application platform powered by Kubernetes. Purpose-built to streamline complex operation…
Introducing Our Smallest, Most Efficient Model: Muse Ember Meta AI just launched their entry in the Claude Haiku/GPT Luna category: Muse Ember, which they describe as: [...] our smallest and most efficient model designed for complex reasoning execution and the work agents repeat …
arXiv:2611.11394v1 Announce Type: new Abstract: Digital innovations have strongly improved ship capabilities, including command, control & communication, navigation and combat management. In the wake of digitisation and geopolitical stress, resilience against cyber-attacks has b…
🧩 Chức năng: Công cụ dòng lệnh
a fast, GPU-accelerated, full-featured IDE and terminal multiplexer, suitable both for automatic and manual programming.
arXiv:2611.15094v1 Announce Type: new Abstract: Medical imaging is essential for diagnosing disease, guiding treatment and monitoring patients over time. Although artificial intelligence has advanced image interpretation, existing medical models often address restricted tasks, w…
Blockchain complexities, such as attacker-deployed sweepers, hobble security controls designed to limit the damage of an exchange compromise.
Text-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings where earlier queries over the same database can supply joins or calculations for …
arXiv:2611.14765v1 Announce Type: new Abstract: Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp, a platform that creates customizable data estates and benchmarks by simulating how business events produc…
🧩 Chức năng: Quản lý hạ tầng/container
Free, open-source playlist sync for Android, Windows, macOS, Linux and Docker. Keeps playlists identical across Spotify, YouTube Music, Apple Music, Amazon Music, TIDAL, Deezer, LiveOne, Anghami, Navidrome, Jellyfin and Plex. Scheduled syncs, easy review of tracks not found. No T…
Google says its new Gemini 4 Hydrogen model can give more helpful answers to complex questions, including "questions with multiple parts, hard-to-understand typos, or highly specific requests." The new model can break down your questions and address each part in its responses. It…
Powered by Gemini 4 Hydrogen, Google's AI Mode is getting better at understanding complex queries, surfacing relevant links, and delivering richer visual responses.
Shoppers using AI chatbots to research products or find places to buy items could be directed to imposters and other risky websites, a new study found. The study conducted by IP protection firm Podqi and shared exclusively with The Verge prompted ChatGPT, Gemini, and Perplexity w…
In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what const…
Microsoft warned customers earlier this week that the November 2026 security updates may break printing for documents with complex formatting. [...]
arXiv:2611.12938v1 Announce Type: new Abstract: We study when and how multimodal input improves knowledge graph question answering (KGQA) in large vision--language models. Using a controlled evaluation over 1,500 WebQSP and CWQ questions and six VLMs within a fixed KGQA pipeline…
arXiv:2611.12940v1 Announce Type: new Abstract: Reinforcement Learning has achieved tremendous success in recent years. Extending its scope from the traditional complex games such as Atari, Go, Pokeman, and Chess, reinforcement learning has caught researchers' attention on model…
System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on…
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.
arXiv:2611.10349v1 Announce Type: new Abstract: Recommender systems are transitioning from static retrieval engines into interactive assistants grounded in physical environments. However, current studies largely neglect the combined complexities of spatial navigation, visual gro…
arXiv:2611.10360v1 Announce Type: new Abstract: Accurate indoor localization on resource-constrained edge devices remains challenging due to the tension between modeling fidelity and computational efficiency. Wi-Fi Channel State Information (CSI) enables low-cost deployment usin…
arXiv:2611.11355v1 Announce Type: new Abstract: CAPTCHAs can protect websites from malicious attacks. As a typical representative of behavior CAPTCHAs, slide puzzle CAPTCHAs have become increasingly popular in recent years due to their user-friendliness and high security. Previo…