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 = 5473, 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 …
We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning archite…
arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…
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…
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…
Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a de…
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:2611.22589v1 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:2611.21932v1 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:2611.15006v1 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…
We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents…
arXiv:2611.18866v1 Announce Type: new Abstract: In cinematic storytelling, sound and visual transitions do not always coincide in lockstep: dialogue frequently bridges across cuts to reveal reactions or introduces new scenes via J- and L-cuts, while deliberate silences pace the …
arXiv:2611.19551v1 Announce Type: new Abstract: Payment operations requested by an AI agent may remain executable, or their outcomes unresolved, after the agent has stopped. We study when a trusted payment service can account for every payment in an epoch and exclude further pay…
Paper tổng hợp về 'Human-Agent Systems': những thách thức khi agentic AI thực thi task dài hạn thay mặt con người, nhấn mạnh tương tác human-agent, phối hợp năng lực và duy trì mối quan hệ trong môi trường socio-technical. Áp dụng khung AAMAS cho các hệ thống agent. Hữu ích nếu bạn xây agent cần phối hợp với người dùng.
arXiv:2611.21925v1 Announce Type: new Abstract: Speculative-diffusion decoding uses a small parallel drafter model to generate b draft tokens in one forward pass, which then undergo parallel verification via a larger target model. Faster inference can be achieved when multiple d…
arXiv:2611.21948v1 Announce Type: new Abstract: The regulation of Artificial Intelligence is susceptible to various forms of capture by industry actors that hold undue influence over the policymaking process, due in part to their information advantage in developing these technol…
arXiv:2611.21951v1 Announce Type: new Abstract: Hate speech remains a persistent and evolving threat on online platforms. The widespread use of large language models (LLMs) further intensifies this problem by making hateful content easier and cheaper to generate at scale. Althou…
arXiv:2611.21621v1 Announce Type: cross Abstract: As the Internet connects more of the world, software vulnerabilities create growing security risks. Because software developers are responsible for building and maintaining secure applications, they rely on tools and techniques t…
arXiv:2611.14548v1 Announce Type: new Abstract: Can a coding agent fix a user's repository while also completing and delivering work the user never requested? In this paper, we introduce SideTaskBench to measure this failure where third-party technical references induce agents t…
arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…
Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment wi…
Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, t…
arXiv:2611.18793v1 Announce Type: new Abstract: Purpose: Multimodal medical imaging fusion (MMIF) is an increasingly important approach to breast cancer detection (BCD), as different imaging modalities rely on different physical principles and provide complementary information. …
arXiv:2611.18971v1 Announce Type: new Abstract: Child safety in AI depends on the accurate identification of minor users. Young children tend to talk rather than type when interacting with AI, so in practice this identification requires predicting age from speech. We evaluated w…
arXiv:2611.18909v1 Announce Type: new Abstract: Genomic data sharing is essential for biomedical research but introduces significant privacy risks, including membership inference attacks, in which an adversary determines whether a specific individual's data was used in a study. …
arXiv:2611.20115v1 Announce Type: new Abstract: Advancements in artificial intelligence (AI) have accelerated digital content generation and intensified concerns around fraud, misuse, counterfeiting, and content provenance. Defensive image watermarking provides a practical mecha…
arXiv:2611.20459v1 Announce Type: new Abstract: AI models can exhibit deceptive behaviors such as strategically underperforming on evaluations (sandbagging), faking alignment, or covertly acting on behalf of a hidden principal. Safe deployment therefore requires auditing techniq…
arXiv:2611.20470v1 Announce Type: new Abstract: Text-to-image diffusion services require both traceability of generated content and differentiated access to generation capabilities. However, existing watermarking methods commonly expose watermark control through mechanisms beyon…
arXiv:2611.17681v1 Announce Type: new Abstract: Complete game generation requires agents to coordinate rules, interactions, states, and presentation over a long development process. A single aggregate score obscures which capabilities are implemented and which requirements remai…
arXiv:2611.17710v1 Announce Type: new Abstract: Multilingual dementia detection is essential for scalable and equitable screening. In recent years, automated speech analysis has emerged as a promising approach for supporting dementia detection by enabling non-invasive and scalab…
arXiv:2611.17796v1 Announce Type: new Abstract: Daily GPU rental-price benchmarks can fail when marketplace quotes are missing. This article stress-tests a fixed equal-weight median rule under four imposed masking mechanisms and four benchmark-level recovery methods. Across 5,80…
arXiv:2611.17596v1 Announce Type: new Abstract: Evaluating tight Differential Privacy (DP) parameters for DP matrix factorization with privacy amplification by sampling requires analyzing high-dimensional, correlated Gaussian mixtures. Because integrating these mixture distribut…
arXiv:2611.18126v1 Announce Type: new Abstract: Windows Hello is the primary authentication mechanism on over one billion Windows 11 devices, supporting PINs as short as four digits. Such low-entropy PINs are viable only because the TPM's anti-hammering protection mitigates brut…
arXiv:2611.17684v1 Announce Type: cross Abstract: Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network …
arXiv:2603.10099v2 Announce Type: replace-cross Abstract: The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed B…
Meetings last up to an hour, and nobody knows in advance how many people will speak. Neural diarizers with a fixed number of output slots, such as Streaming Sortformer and Nemotron-3, are accurate and run online, but they cannot name more speakers than they have slots. We remove …
arXiv:2611.15958v1 Announce Type: new Abstract: Static Random Access Memory (SRAM) Physical Unclonable Functions (PUFs) are a promising technology in the realm of random number generation for key generation, but for PUF-based authentication, they have been sidelined due to their…
arXiv:2611.17003v1 Announce Type: new Abstract: Crypto agility maturity models aim to support organizations in preparing for cryptographic transitions, such as migrating to post-quantum cryptography. Recognizing the importance of measurable maturity, NIST references several such…