AI agents topped the list of planned investments in behavioral monitoring in Abnormal AI’s 2026 State of Behavioral Security Report. Asked where their organizations would invest most over the next two years, 43% of respondents chose AI agents, more than three times the share who …
⏱ Độ trễ thật của tab này: trung bình 6.2 giờ sau khi CVE được công bố (n = 5307, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Cybercriminals are using AI agents to coordinate attacks, stolen credentials to access linked services, and tools that interfere with intrusion detection and system recovery, according to Acronis TRU Cyber Pulse 2026. One operator coordinates activity across several countries In …
arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…
arXiv:2611.10453v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entir…
arXiv:2611.10395v1 Announce Type: new Abstract: Information-flow control (IFC) is a promising approach to enforce policy in agentic AI systems. However, IFC suffers from label creep, a phenomenon where monotonically increasing security labels propagate through a system and progr…
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…
arXiv:2611.10756v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as shared multi-tenant services, relying on advanced optimizations like KV cache and prefix sharing to improve throughput and reduce latency. However, these optimizations intro…
arXiv:2611.10830v1 Announce Type: new Abstract: Agentic AI ecosystems increasingly rely on reusable agent skills that combine executable code, natural-language instructions, configuration artifacts, and external tool integrations. These hybrid artifacts create software supply-ch…
arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act be…
arXiv:2611.10947v1 Announce Type: new Abstract: Cloud infrastructure threat modeling lacks empirical validation of AI-discovered threats. We present a three-phase methodology of multi-agent threat discovery, automated exploit synthesis, and non-destructive live validation, and a…
arXiv:2611.11104v1 Announce Type: new Abstract: As a core protocol for integrating large language models (LLMs) with external data sources and tools, the Model Context Protocol (MCP) has quickly become a key interface in emerging AI agent systems. As the MCP ecosystem expands, r…
arXiv:2611.11266v1 Announce Type: new Abstract: As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate across sessions through poisoned shared state, long-context documents, and trusted pe…
arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…
A leaderboard is not a distribution. Continue reading on MeetCyber »
A security researcher’s AI agent breached an internal sales application used by WorkOS’s go-to-market teams, the developer platform provider confirmed on Friday. “The researcher was conducting cybersecurity benchmark evaluations using ARTEX when their agent escaped its isolated t…
Wirken is an open-source gateway that sits between messaging apps and AI agents. It assumes any agent can be turned against its owner and limits what a compromised one can reach. Take an agent that reads your chats and email, holds the keys to your accounts and can run commands. …
🎯 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:2611.09734v1 Announce Type: new Abstract: Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing …
arXiv:2611.08516v1 Announce Type: cross Abstract: Autonomous coding agents such as Google Antigravity (agy), Anthropic Claude Code (claude), and OpenAI Codex CLI (codex) execute multi-step software engineering workflows on workstations and cloud hosts. Existing agent environment…
Why Most Guides Get This Wrong Continue reading on Medium »
OpenAI has introduced GPT-6 Cyber, a version of GPT-6 Astra trained to find software vulnerabilities, test how attackers could exploit them, and help develop fixes. The model is designed for authorized security testing of websites and applications. Vulnerability research and secu…
The AI running inside large companies has stopped waiting for permission. Across five categories of AI, from chatbots to process automation, more than half of 3,600 business decision-makers say the systems their teams use can act within defined rules without routine review, or fi…
arXiv:2611.06996v1 Announce Type: new Abstract: The policy that converts runtime estimates of an autonomous agent's condition into operational authority is rarely specified or measured. We empirically characterize the Trust Responsive Authorization Policy (TRAP), which maps an A…
arXiv:2611.07372v1 Announce Type: new Abstract: An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning and harness optimization, we propose the third direction: optimization over sta…
arXiv:2611.07508v1 Announce Type: new Abstract: AI agents that work for an individual over time may also help that individual serve external clients. We define a personal external service agent as an agent authorized and continuously managed by a specific individual to accept cl…
arXiv:2611.07528v1 Announce Type: new Abstract: LaCAM is a search-based solver for multi-agent pathfinding (MAPF) that runs a depth-first search over joint configurations, using PIBT to generate successors and lazily adding single-agent constraints to explore alternatives. Altho…
arXiv:2611.07667v1 Announce Type: new Abstract: The performance of multi-agent LLM systems depends not only on the capabilities of the underlying models but also on information-sharing policies, which govern what information each agent observes and at what level of detail. But d…
arXiv:2611.07689v1 Announce Type: new Abstract: Large language model agents are increasingly deployed through the Model Context Protocol (MCP), which allows them to discover and invoke tools across multiple servers at runtime. Existing MCP benchmarks primarily measure task compl…
arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defe…
arXiv:2605.03158v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) systems must link exploit code, advisories, and fix commits to the vulnerabilities they concern, and they must do so for vulnerabilities disclosed after training. HackerSignal is a public corpus …
arXiv:2609.16541v2 Announce Type: replace Abstract: We have applied a novel combination of classic relational database modeling and modern reinforcement learning to automated intrusion response to enable inductive decision agents. Unlike previous work in the area, our approach a…
Cyberhaven has introduced Agentic Data Security (ADS), to help CISOs, data security teams, insider risk teams, and AI governance leaders say yes to AI agents without losing control of their data. Agentic Data Security shows security teams what every AI agent does with company dat…
Arkose Labs has expanded Arkose Agent Trust Manager to help businesses control agentic traffic. Companies can classify agent sessions, apply allow, monitor or block policies at each step of the customer journey, and track the same agent across multiple networks. The need is urgen…
Every autonomous AI agent deployed across your enterprise today is a new proxy identity operating inside your perimeter. The post The Agent Smith Dilemma: Governing Agentic Identities appeared first on SecurityWeek .
Bots follow a script. AI agents work toward a goal and choose their own steps, which makes them harder to catch. In this Help Net Security interview, Zohaib Ahmed, CEO of Resemble AI explains how agents arrive as declared, undeclared or disguised traffic, and why binary bot detec…
Customer control, account security and ease of use are influencing the adoption of AI agents that make purchases, book services and access personal information, according to Okta’s 2026 Customer Identity Trends Report. Consumers’ willingness to delegate depends on what an agent c…
arXiv:2611.05390v1 Announce Type: new Abstract: Multi-agent language-model systems often add a reviewer to improve an upstream agent's decision. Yet a reviewer can both repair errors and replace decisions that were already correct. We study this as a problem of institutional jur…
arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represe…
arXiv:2611.05620v1 Announce Type: new Abstract: On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are…
arXiv:2611.05709v1 Announce Type: new Abstract: LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how critical thought supervision is for agents' ultima…
arXiv:2611.06197v1 Announce Type: new Abstract: Web tracking studies largely rely on automated crawlers, yet their measurements can differ from what people encounter while browsing. Conventional crawlers follow predefined navigation rules, whereas LLM-driven agents decide how to…