Malware can lurk inside just 0.00001% of a neural network. How, then, can any user tell it's there?
⏱ Độ trễ thật của tab này: trung bình 7.0 giờ sau khi CVE được công bố (n = 5140, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Companies deploying AI agents have the illusion of control, but several incidents demonstrate that businesses need to be ready to enforce directions.
🎯 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
Attackers' AI agents have been hunting for weak spots in internet-exposed AI apps such as LiteLLM, One API, and Dify to steal the AI provider keys stored inside, according to the agents' own records. The records, which Amazon's threat intelligence team captured with decoy server…
Palo Alto Networks will acquire Applied Compute, a platform for post-training and inference of open-weight AI models. The all-stock transaction is valued at $4.5 billion, subject to adjustments. The acquisition will bring Applied Compute’s platform and world-class AI research tea…
The all-stock deal will give the cybersecurity company a platform for fine-tuning and running open-weight AI models in public and sovereign clouds. The post Palo Alto Networks to Buy AI Startup Applied Compute for $4.5 Billion appeared first on SecurityWeek .
The commercial kit uses attacker-supplied AI models to personalize lures, evade spam filters, and scale campaigns to tens of thousands of targets.
A Lack of ownership verification on the Hugging Face platform allowed researchers to take control of Kokoro, a text-to-speech model used in projects from Google, NVIDIA, AMD, Intel, and Amazon Web Services. [...]
The lawsuit alleges that OpenAI misled and endangered the public and users by knowingly developing advanced AI models without necessary safeguards. The post California Sues OpenAI, Seeking Court-Ordered Changes After the Hugging Face Hack appeared first on SecurityWeek .
NATO’s Communications and Information Agency (NCIA) gives NATO’s core institutions access to OpenAI’s cybersecurity models to help protect Allied networks. NATO has used up to 300 billion raw input and output tokens a month. Access comes through Daybreak, OpenAI’s program for vet…
Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]
Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]
A Lack of ownership verification on the Hugging Face platform allowed researchers to take control of Kokoro, a text-to-speech model used in projects from Google, NVIDIA, AMD, Intel, and Amazon Web Services. [...]