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…
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5381, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
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:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…
External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it fo…
arXiv:2611.10542v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules imp…
arXiv:2611.14864v1 Announce Type: new Abstract: An AI agent's decision not to act can itself become an attack surface. We study warning-induced over-abstention, an availability attack in which adversaries place fabricated risk warnings in low-trust content to prevent legitimate …
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:2611.17703v1 Announce Type: new Abstract: Healthcare organizations collect huge amounts of patient data from clinical records, medical tests, monitoring systems, and healthcare services. Such data can underpin intelligent healthcare analytics but remains distributed across…
arXiv:2611.18055v1 Announce Type: cross Abstract: DeCompCert is a Rocq-verified decompiler for AArch64 assembly generated by CompCert. It reconstructs CompCert C through nine reverse passes, combining deductively verified transformations with translation validation. Untrusted OC…
arXiv:2611.18363v1 Announce Type: cross Abstract: We explore the adaptability of neural image watermarking models; the extent to which one watermarking method can be transformed into another through lightweight adaptation. We introduce a framework that enables encoder-decoder wa…
arXiv:2611.14978v1 Announce Type: new Abstract: Third-party low-rank adaptation (LoRA) adapters are tailored to perform decision tasks such as content moderation and function selection. However, in the real world, quantized deployments carry a potential threat in that an adapter…
arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…
arXiv:2611.15737v1 Announce Type: new Abstract: A vulnerability detector is only as trustworthy as the benchmark that scores it, and today's real-world datasets tend to flatter detectors. They are often built once and never refreshed, so they quickly miss new vulnerabilities, th…
arXiv:2611.12970v1 Announce Type: new Abstract: Large Language Models (LLMs) show strong potential for social media content moderation, but their trustworthiness beyond overall accuracy remains underexplored. We introduce TrustMod-SM, a benchmark of roughly 29,000 instances acro…
arXiv:2611.16128v1 Announce Type: new Abstract: The CoordX Protocol carries signed and encrypted entries between parties. It proves who wrote each entry and who had permission to write it. It does not say what an entry means. That task belongs above the protocol layer. This pape…
While search agents demonstrate impressive capabilities in multi-step question answering, their robustness to poor-quality evidence remains under-explored. Such evidence is rare in benchmark corpora, and resulting failures are hard to reproduce. We propose DeepStress, a dynamic s…
arXiv:2611.12936v1 Announce Type: new Abstract: Intelligent landslide detection is essential for disaster prevention. However, existing models primarily focus on isolated visual tasks, require extensive labeled data, and lack deep analytical and scene-understanding capabilities.…
arXiv:2611.13042v1 Announce Type: new Abstract: Artificial intelligence (AI) systems now produce research results in bulk: in October 2026 a single laboratory released more than 700 AI-generated mathematics manuscripts, only part of them with machine-checked proofs. Such volumes…
arXiv:2611.13437v1 Announce Type: new Abstract: Enforcing export controls on AI accelerators requires verifying where a chip operates after deployment. Round-trip time measurements can bound a chip's distance from a trusted landmark, but any jitter in honest replies forces the v…
arXiv:2611.13965v1 Announce Type: new Abstract: MiniApps are increasingly central to super-app ecosystems, yet architectural differences complicate the transfer of security analysis techniques across platforms. Existing WeChat analyzers rely on packaged applications and platform…
arXiv:2611.14317v1 Announce Type: new Abstract: Data spaces like the European Health Data Space (EHDS) require the protection of sensitive data in studies during the data's processing and the study's release alike. In this work, we investigate how to implement this mandate using…
arXiv:2611.10020v1 Announce Type: new Abstract: Secure aggregation in domains such as federated learning, Internet of Things, and voting requires operating on private inputs while preserving confidentiality, verifying that each input satisfies constraints, and avoiding trusted p…
arXiv:2611.10099v1 Announce Type: new Abstract: We study a safety harness that improves itself without touching model weights. Enmo Safety wraps a chat model with a deterministic input assessment, trigger-matched safety guidance, spotlighting of untrusted content, and an output …
arXiv:2611.10622v1 Announce Type: new Abstract: Vector search on untrusted infrastructure exposes the \emph{query embedding}, a faithful summary of the user's intent. Fully homomorphic encryption can hide the query, but existing approaches still require a full scan followed by r…