arXiv:2611.23346v1 Announce Type: new Abstract: Long-horizon LLM agents across codebases, web browsers, and enterprise infrastructure rely on an execution harness to move state between the working context, session history, persistent memory, and external environment. While conve…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5388, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
In this Help Net Security interview, Peter Stöckli, Security Researcher at GitHub, explains how the team uses AI agents to audit software for vulnerabilities. The discussion covers why the work started with authentication and authorization bugs, how prompts are tested and trimmed…
arXiv:2611.19215v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionate…
Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to boo…
🧩 Chức năng: Sinh video bằng AI (text/ảnh → video)
Kho tài liệu tổng hợp hướng dẫn, cấu hình tham số và bộ prompt mẫu tối ưu cho mô hình tạo video AI Seedance 2.5 / 2.5 Flash qua MuAPI. Phù hợp cho lập trình viên muốn tham khảo cách tạo prompt sinh video nhất quán.
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
arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…
arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…
arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …
ChatGPT can receive audio prompts from your microphone faster now with a Live Dictation feature that transcribes as you speak, rather than waiting until you finish recording. It's rolling out now globally on all ChatGPT plans on the web, desktop app, and iOS and Android apps. Whi…
arXiv:2611.22238v1 Announce Type: new Abstract: Coding agents repeatedly send their conversation history to a language model. Adding useful code may reduce search, while removing old tool outputs may shorten later prompts. But do these changes reduce the cost of solving a task? …
🧩 Chức năng: Công cụ quanh mô hình ngôn ngữ (prompt/agent)
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
arXiv:2611.19199v1 Announce Type: new Abstract: LoCoMo is a widely reported benchmark for long-term conversational memory, but published scores mix memory quality with choices of answer prompt, judge and baseline layout that are rarely reported together. We measure how much thes…
🧩 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…
🧩 Chức năng: Sinh video bằng AI (text/ảnh → video)
140 curated Seedance 2.5 Flash video prompts with preview frames, grouped by use case.
arXiv:2611.19090v1 Announce Type: new Abstract: As Large Language Models (LLMs) become used more commonly across a variety of fields, a growing body of research has highlighted particular concerns surrounding model security. Notably, prompt injection attacks, where malicious ins…
arXiv:2611.20470v1 Announce Type: new Abstract: Text-to-image diffusion services require both traceability of generated content and differentiated access to generation capabilities. However, existing watermarking methods commonly expose watermark control through mechanisms beyon…
arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …
arXiv:2611.14769v1 Announce Type: new Abstract: Arena-style rankings of language models are a widely used evaluation framework in online leaderboards, research papers, and model evaluation in production. These rankings aim to realistically assess model performance using pairwise…