From autonomous pentest agents to LLM red-teaming kits: the new AI security tools worth your time, what they actually do, and where they… Continue reading on Medium »
⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5340, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Picus Security has announced Picus Autonomous Penetration Testing, an agentic pentesting capability that puts AI agents on the offensive: they think like attackers, chain real exploits toward an organization’s crown jewels, and prove what a breach would look like, under governanc…
Our analysis of how attackers used the open-source Cairn AI agent framework to autonomously breach semiconductor, defense and civic targets. The post Attackers Use Autonomous AI to Target Semiconductor, Defense and Civil Society Sectors appeared first on Unit 42 .
arXiv:2611.12941v1 Announce Type: new Abstract: The rapid proliferation of autonomously acting AI agents makes the governance of agentic systems urgent. We propose the competence circuit, summarized as IKC + KC + C, that decomposes an agent's real-world impact into three pathway…
arXiv:2611.13020v1 Announce Type: new Abstract: Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although …
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:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an …
OverServe: kỹ thuật resource amplification attack nhắm vào SaaS agents — tenant xấu dùng prompt khai thác quyết định 'khi nào agent tự dừng' để kéo dài execution và đốt tài nguyên model/tool của provider (đặc biệt model subscription-based). Đáng chú ý với ai xây/thẩm định AI agent trong SaaS vì dễ bị lạm dụng chi phí.
🎯 Kẻ tấn công làm gì (từng bước)
- Tìm đúng đường dẫn/API có xử lý dữ liệu người dùng gửi lên
- Gửi payload đã chế để máy chủ thực thi lệnh/mã
- Dùng quyền của tiến trình web để đọc file, cài backdoor, mở kênh ra ngoài
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Tiến trình web (php-fpm/nginx/java) sinh tiến trình con bất thường: sh, bash, curl, wget
- Kết nối ra ngoài từ máy chủ tới IP lạ đúng lúc có request lạ
- File mới xuất hiện trong thư mục tải lên/tạm
🛡 Phòng ngay (làm được hôm nay)
- Vá ngay bản có lỗi (ưu tiên số 1)
- Chặn tạm đường dẫn/API bị lỗi ở WAF/reverse proxy nếu chưa vá được
- Chạy tiến trình web bằng user quyền thấp, tắt các hàm shell (disable_functions) nếu dùng PHP
- Bật giám sát tiến trình con của web server để phát hiện lệnh lạ
🧩 Chức năng: Khung/chương trình AI agent tự làm việc nhiều bước
A self-extending AI agent that runs anywhere Termux runs. Writes its own capabilities, remembers across sessions.
arXiv:2611.15189v1 Announce Type: new Abstract: Document editing is among the most common knowledge-work tasks, yet existing benchmarks for evaluating autonomous agents on Word document editing provide fully specified attribute-modification instructions. They do not evaluate age…
🧩 Chức năng: Khung/chương trình AI agent tự làm việc nhiều bước
Dexter là một autonomous agent mã nguồn mở được thiết kế để thực hiện nghiên cứu tài chính chuyên sâu. Thích hợp để tích hợp vào các workflow tự động hoá phân tích dữ liệu tài chính.
Amazon Web Services has released AWS Emulator, a free tool that simulates AWS services on a developer’s laptop, a development server or in a continuous integration (CI) pipeline. The company says autonomous AI agents wrote the tool entirely, with no code written or reviewed by it…
Orca Security has announced new capabilities to help organizations discover and secure AI-generated applications and autonomous agents across their cloud environments. The expansion builds on Orca’s AI Security offering, enabling security teams to uncover previously unknown AI ap…
arXiv:2611.12933v1 Announce Type: new Abstract: Closed-loop autonomous experimentation can accelerate scientific discovery, but implementation effort limits accessibility. Agentic systems may lower this barrier, although sustained operation on physical instruments remains largel…
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:2611.13406v1 Announce Type: new Abstract: Autonomous language-model agents can drive industrial controllers over fieldbus protocols, probing a plant at machine speed and in coordinated swarms. We present Talos, an inline gate that judges every agent request to a controller…
What if you could give an AI penetration tester a single application URL and let it explore the application, investigate potential… Continue reading on Medium »
Our analysis of how attackers used the open-source Cairn AI agent framework to autonomously breach semiconductor, defense and civic targets. The post Attackers Use Autonomous AI to Target Semiconductor, Defense and Civil Society Sectors appeared first on Unit 42 .
🎯 Kẻ tấn công làm gì (từng bước)
- Tìm đúng đường dẫn/API có xử lý dữ liệu người dùng gửi lên
- Gửi payload đã chế để máy chủ thực thi lệnh/mã
- Dùng quyền của tiến trình web để đọc file, cài backdoor, mở kênh ra ngoài
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Tiến trình web (php-fpm/nginx/java) sinh tiến trình con bất thường: sh, bash, curl, wget
- Kết nối ra ngoài từ máy chủ tới IP lạ đúng lúc có request lạ
- File mới xuất hiện trong thư mục tải lên/tạm
🛡 Phòng ngay (làm được hôm nay)
- Vá ngay bản có lỗi (ưu tiên số 1)
- Chặn tạm đường dẫn/API bị lỗi ở WAF/reverse proxy nếu chưa vá được
- Chạy tiến trình web bằng user quyền thấp, tắt các hàm shell (disable_functions) nếu dùng PHP
- Bật giám sát tiến trình con của web server để phát hiện lệnh lạ
Paper tổng hợp về 'Human-Agent Systems': những thách thức khi agentic AI thực thi task dài hạn thay mặt con người, nhấn mạnh tương tác human-agent, phối hợp năng lực và duy trì mối quan hệ trong môi trường socio-technical. Áp dụng khung AAMAS cho các hệ thống agent. Hữu ích nếu bạn xây agent cần phối hợp với người dùng.
arXiv:2611.12958v1 Announce Type: new Abstract: Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and …
arXiv:2611.15225v1 Announce Type: new Abstract: Surround-view video understanding in autonomous driving is a crucial capability for Multimodal Large Language Models (MLLMs) to achieve reliable driving reasoning. Real-world driving often requires information beyond the front-view…
arXiv:2611.15238v1 Announce Type: new Abstract: Discrete diffusion generation is emerging as a competitive alternative to autoregressive generation by denoising the entire token sequence through iterative refinement. Its global planning and progressive correction capabilities ar…
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 …
In my last post, I wrote about moving Forem’s performance and maintenance work into autonomous loops...
Kai has announced External Attack Surface Management (EASM), now available on the Kai Autonomous Defense Platform. The company also launched Kai Labs, an expanded research team focused on the hardest open problems where AI meets security. Most exposure management programs only se…
The Series C round will fund international expansion and more autonomous features for the firm’s device security platform. The post Finite State Raises $27 Million to Secure Software and Firmware in Connected Devices appeared first on SecurityWeek .
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…
New AI Harms Taxonomy traces how harm moves through AI systems, from misleading chatbot answers to compromised autonomous agents, and identifies where defenses can intervene.
arXiv:2611.10031v1 Announce Type: new Abstract: Autonomous agents increasingly execute consequential actions on behalf of users, but ordinary middleware guardrails do not provide cryptographic proof that a policy was actually enforced. Their verdicts leave counterparties depende…
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…
Embed Security announced new capabilities that let security teams teach Embed how they investigate, what matters in their environment, and how to improve their detections. With customer-built iSteps, expanded NoiseIQ Memories, and Detection Engineering, organizations can extend E…