arXiv:2611.21956v1 Announce Type: new Abstract: We audit instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog. The research question we answer with this experiment is which models disclose a protected secret embedded in the system prom…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5442, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.22223v1 Announce Type: new Abstract: Large Language Model (LLM)-based web agents rely on data minimization and least privilege to protect user privacy. We show that these principles are necessary but insufficient: they constrain authorized sources, but not higher-sens…
arXiv:2611.22519v1 Announce Type: cross Abstract: GitHub natively supports workflow automation through GitHub Actions, now the dominant CI/CD tool on the platform. Yet keeping these workflows secure remains an ongoing burden: maintainers often patch a vulnerability on the defaul…
arXiv:2611.22888v1 Announce Type: new Abstract: Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained ex…
arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…
arXiv:2611.19333v1 Announce Type: new Abstract: Enterprise information is commonly stored across multiple platforms rather than in one centralized location. Answering questions about workplace activities may require information from several sources, including project documents, …
arXiv:2611.19465v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) security agents requires reproducible environments whose workflow difficulty can be varied and whose failures can be diagnosed. We present VAST (Verifiable Adversarial Scenario Training & Evalu…
arXiv:2611.19536v1 Announce Type: new Abstract: AI coding agents now push code, publish packages, call model APIs and operate cloud resources on behalf of developers. They authenticate to these services with the same bearer secrets humans use, personal access tokens, API keys an…
arXiv:2611.19598v1 Announce Type: new Abstract: Current multi-agent authorization architectures prioritize system integrity over human outcomes. While recent models successfully prevent privilege escalation, they externalize the cost of failure onto the human operator. Re-center…
arXiv:2611.19764v1 Announce Type: new Abstract: Autonomous coding agents (such as Antigravity, Claude Code, Cursor, and OpenHands) rely on third-party tools to inspect files, run commands, and call external APIs. Today's security auditors evaluate these tools almost entirely in …
arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a ben…
arXiv:2611.20671v1 Announce Type: new Abstract: Tamarin-based formal verification of security protocols requires expert-authored multiset rewriting rules and temporal-logic lemmas. Translating a natural-language protocol description into a complete formal model with an LLM is ha…
arXiv:2611.17534v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for investigative tasks over incomplete evidence, such as cybersecurity alert triage, but reinforcement learning (RL) for such tasks is difficult: intermediate steps have no v…
arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…
arXiv:2611.22971v1 Announce Type: new Abstract: Safety benchmarks for computer-use agents (CUAs) place the harm either in the intent of the task or on a single screen: a malicious instruction, an injected command, a phishing page. An agent that checks the task and each screen in…
arXiv:2611.19295v1 Announce Type: new Abstract: Deception (honeypots, decoys and canary credentials) rests on a simple premise: legitimate users never touch a fake asset, so any touch is a high-confidence signal. We ask whether that premise holds when the attacker is a large lan…
arXiv:2611.19886v1 Announce Type: new Abstract: Large Language Model (LLM) agents interact with their environments through tools, reading repositories, running builds, and pushing code. When a tool fails with an ordinary error, such as a rate limit or a timeout, the agent can fa…
arXiv:2611.20045v1 Announce Type: new Abstract: Deep research and agentic search agents autonomously retrieve content from the open web and generate reports with citations, and their outputs are often taken directly as research conclusions. This paper systematizes security resea…
arXiv:2611.20223v1 Announce Type: new Abstract: Artificial intelligence is increasingly integrated into healthcare systems, from clinical information retrieval to workflow automation and decision support, which introduces new security, privacy, and trust risks with direct implic…
arXiv:2611.20454v1 Announce Type: new Abstract: Latent multi-agent communication directly transfers Key-Value (KV) cache tensors between transformer-based agents, bypassing text serialization entirely. While computationally efficient and reasoning accurate, this communication ch…
arXiv:2611.17918v1 Announce Type: new Abstract: Scaling laws indicate that the generalization error of a large language model (LLM) decreases monotonically with model size once data is sufficient, and the corollary that larger models outperform smaller ones is now widely accepte…
arXiv:2611.18133v1 Announce Type: new Abstract: Large language model (LLM) agents keep a long-term memory that the model itself writes: summaries, extracted facts and embeddings derived from what users said. Deleting a message is therefore not enough: its derivatives, storage re…
arXiv:2611.22583v1 Announce Type: new Abstract: Tool-using language-model agents must act on information from untrusted emails, webpages, and documents. This creates a central security challenge: malicious instructions and legitimate task directives can arrive through the same i…
arXiv:2611.22274v1 Announce Type: cross Abstract: In traditional recommender systems (RSs), textual information typically serves as auxiliary signals for representation learning. In contrast, in LLM-based RSs, textual information becomes the primary medium for recommendation gen…
arXiv:2611.22288v1 Announce Type: cross Abstract: Large-language-model agents now close the industrial predictive-maintenance loop, reading sensor windows, retrieving procedures and dispatching work orders. Two attack channels meet there: injected text in a retrieved document ca…
arXiv:2611.20765v1 Announce Type: new Abstract: Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically d…
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:2611.16588v1 Announce Type: new Abstract: Affected-version ranges in vulnerability databases decide which deployments scanners, patching pipelines, and incident responders treat as vulnerable, yet these ranges are often incomplete, so vulnerable releases are silently treat…
arXiv:2611.21702v1 Announce Type: new Abstract: Open-weight language models can continue generating after their released weights are modified, while a watermark verifier still scores outputs against the original base and marked models. We study how such modifications change the …
arXiv:2611.21777v1 Announce Type: new Abstract: Cross-chain bridges have suffered substantial asset losses due to vulnerabilities in their on-chain programs. On Solana, missing validation checks can enable exploits even when the underlying blockchain operates correctly. The abil…
arXiv:2611.21822v1 Announce Type: new Abstract: Vibe coding is reshaping software development, enabling faster implementation and allowing individuals with limited programming experience to describe requirements in natural language while AI agents write, test, and deploy the cod…
arXiv:2611.21936v1 Announce Type: new Abstract: Traditional malware classification methods struggle to keep pace with rapidly evolving threats. Image-based malware classification offers a promising alternative by converting malware binaries into grayscale images for analysis wit…
arXiv:2611.22243v1 Announce Type: new Abstract: In LLM serving systems with prefix caching, each KV block of a shared system prompt is held in GPU memory as a single physical copy, which every request with that prompt reads. Our earlier work measured change and showed that one b…
arXiv:2611.22408v1 Announce Type: new Abstract: Security-minded verification of autonomous and robotic systems presupposes an attacker, yet the path from a threat catalogue to a checkable attacker model is still traversed by hand. This research preview presents the theory and co…
arXiv:2611.22479v1 Announce Type: new Abstract: -05-X-03), Known Exploited Vulnerabilities (KEV) catalogs, and exploitation sightings. We introduce an evidence model implemented in Vulnerability-Lookup that selects the earliest evidence for each lifecycle event, distinguishes …
arXiv:2611.22589v1 Announce Type: new Abstract: Large Language Models (LLMs) enable honeypots to generate responses and deceptive artefacts on demand, yet existing approaches evaluate generated content one reply at a time and leave open whether artefacts that jointly describe a …
arXiv:2611.22761v1 Announce Type: new Abstract: Large language models (LLMs) in embodied robots create security dependencies beyond inference. We investigate a network-exposed configuration attack on the Pollen Robotics Reachy Mini Lite, allowing an unauthenticated attacker to r…
arXiv:2611.21932v1 Announce Type: cross Abstract: This study proposes an interesting approach for vehicle-to-vehicle (V2V) communication, which integrates blockchain technology, federated learning (FL), and allocation optimization of latency and resources. The research evaluates…
arXiv:2611.18887v1 Announce Type: new Abstract: AI agent interoperability protocols enable orchestrators to discover and invoke external agents using machine-readable metadata. In the Agent2Agent (A2A) protocol, Agent Cards contain attacker-controllable natural-language fields t…