Bài nghiên cứu mới giới thiệu mô hình Envelope Layer cho LLM Agent, đánh giá trọng lượng các thành phần và cách giải quyết rủi ro khi công cụ MCP và bộ nhớ lâu dài đồng thời tồn tại. Điều này giúp cải thiện an toàn và giảm rủi ro lây nhiễm nội dung độc hại trong AI Agent.
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5445, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
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:2611.20045v1 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:2611.22583v1 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:2611.22288v1 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:2611.23236v1 Announce Type: cross Abstract: LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection…
arXiv:2611.18027v1 Announce Type: new Abstract: Web caches reduce origin load and latency, but automated traffic can either warm them or evict objects shoppers reuse, lowering the cache hit ratio (CHR). Existing bot defenses generally infer automation from User-Agent (UA) string…
arXiv:2611.24662v1 Announce Type: new Abstract: AI-driven attacks learn the models of cyber-physical systems (CPS) by passively observing controller and plant signals, then use this knowledge to act covertly. Because covertness depends on the accuracy of the identified model, de…
arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine…
arXiv:2611.20291v1 Announce Type: new Abstract: LLM serving engines cache prompt prefixes; a cache hit skips computation and returns faster, so a shared cache reveals whether others have sent a given text. Per-account salting closes this channel but forgoes cross-tenant reuse an…
arXiv:2611.15013v1 Announce Type: new Abstract: Machine unlearning lets the owner of large language models (LLMs) remove specific entities from a trained model without retraining from scratch. Existing machine unlearning methods focus on removing the requested entities while mai…
arXiv:2611.21832v1 Announce Type: new Abstract: As AI systems are increasingly used to automate AI R&D, misaligned systems could sabotage research intended to improve model safety and alignment. To stress-test defenses against such sabotage, we use a human expert as a proxy sabo…
arXiv:2611.19864v1 Announce Type: new Abstract: Website fingerprinting (WF) attacks let a passive adversary infer which site a Tor user visits from the encrypted cell sequence. On undefended traffic, hand-crafted-feature attacks are already near-ceiling, so deep learning offers …
arXiv:2611.20594v1 Announce Type: new Abstract: An enterprise breach causes most of its damage after the perimeter is crossed. Once an attacker gains a foothold, they can move laterally to other hosts, take over the trusted services of the network, and encrypt the backups needed…
arXiv:2611.17761v1 Announce Type: new Abstract: Many cyber-physical systems (CPS) are multi-mode: they switch between operating modes with different tasksets and timing parameters in response to physical events or user activity. We show that these mode changes create a timing si…
arXiv:2611.17907v1 Announce Type: new Abstract: We consider a physical layer authentication scenario in which a legitimate user (Alice) communicates with an authenticator (Bob) through a reconfigurable intelligent surface (RIS), controlled by Bob. An attacker (Trudy) aims to imp…
arXiv:2611.16557v1 Announce Type: new Abstract: We consider a physical layer authentication scenario in which a legitimate user (Alice) communicates with an authen- ticator (Bob) through a reconfigurable intelligent surface (RIS), controlled by Bob. An attacker (Trudy) aims to i…