The paper presents RuntimeGuard‑AI, a prototype that links each deterministic AI policy decision to its source code, writes a privacy‑minimizing record at a chosen synchronization point, and returns an Ed25519‑signed receipt indicating whether the write succeeded. After a crash, the system validates the integrity of records, manifests, shard placement, sequence continuity, and replay identity, while an independent attestation path chains committed records into signed Merkle epochs for auditor verification. Performance results on an Apple M4 Pro show high throughput (up to 27,193 requests/s) with low latency when buffering, but throughput drops and latency rises when per‑record data and full synchronization are used, illustrating a clear durability‑latency trade‑off.
By Neeraj Kumar Singh Beshane
The paper proposes a methodological framework to assess large language models (LLMs) as surrogate experts in security surveys, particularly for Security Operations Centres (SOCs). By comparing persona-based and aggregate LLM-generated responses to real SOC professional data, the study evaluates stability, inter-model agreement, and alignment with human answers. Findings reveal that while LLMs produce internally consistent responses, they systematically diverge from experts, showing reduced variance, central tendency bias, and homogenised opinions, indicating they are suitable for piloting and hypothesis generation but not for replacing expert elicitation.
By Despoina Giarimpampa, Roland Meier, Tegawend\'e F. Bissyand\'e, Vincent Lenders, Jacques Klein
The paper introduces FCom‑DICE, a feature‑aware perturbation method that rewires influential edges and adjusts node features to hide a target community from graph neural network (GNN) inference. It shows that concealment effectiveness depends on boundary connectivity and feature similarity, and that FCom‑DICE outperforms structure‑only DICE on synthetic and real networks such as Facebook, Wikipedia, and Bitcoin Transactions while preserving key structural and feature properties.
By Dalyapraz Manatova, Pablo Moriano, L. Jean Camp
The paper presents a validated protocol for adapting drone‑based crowd‑counting models to the extreme conditions expected at the 2034 FIFA World Cup in Saudi Arabia. Using 525 controlled runs and a full‑resolution corpus, the authors demonstrate that label‑free adaptation can recover 31‑49% of shift‑induced error across multiple corruptions and severities, achieving a 41.8 MAE improvement over a frozen source model. They also introduce a severity law, a stability budget, and a flux‑based risk module that detects real congestion episodes, culminating in a six‑point deployment protocol for safe aerial crowd monitoring.
By AlAnoud AllGhayth, AlJawharh AlOtaibi, Jude AlSubaie
The paper examines how multi‑level fairness techniques—combining several bias‑mitigation steps—can reduce biases across patient demographics in health informatics. It reviews current literature, identifies gaps in implementation and reporting of health equity outcomes, and evaluates the role of reporting standards such as MINIMAR and TRIPOD in enhancing transparency. The authors conclude with recommendations to improve reporting transparency, broaden adoption of multi‑level fairness methods, and explicitly prioritize health equity in future research.
By Nick Souligne, Vignesh Subbian
The paper introduces TSN4PI, a unified framework for tracking the evolution of political ideologies on social media. It combines a PIDN module that uses large language models, style transfer, and unsupervised domain adaptation to detect ideologies and filter noise, with a PIPN module that employs temporal graph neural networks to predict future ideological shifts. The authors release two large-scale datasets and validate the approach on platforms such as X and Truth Social, offering empirical insights into political polarization and online ideology evolution.
By Yijie Xu, Chao Wang, Hui Xiong
arXiv:2608. 17434v1 Announce Type: new Abstract: We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B.
By Tao Jiang, Minbo Gao, Shaowei Cai
The paper proposes a Learnware-based framework for deploying scene‑specific CSI feedback models in 6G systems. A centralized AI data center maintains a catalog of pre‑trained models, each tagged with semantic and statistical specifications. Base stations retrieve the most relevant model using only statistical fingerprints, which reduces data privacy risks, lowers retrieval latency, and cuts fine‑tuning effort, achieving up to 57.7% performance gains over a general model.
By Xiangyi Li, Jiajia Guo, Chao-Kai Wen, Xin Geng, Shi Jin, Zhi-Hua Zhou
CoAL‑RAG is a complexity‑aware legal retrieval‑augmented generation method that adapts its retrieval strategy based on a multi‑dimensional evaluation of question essence and retrieval consistency. It quantifies reasoning demand from the logical structure of a question and uses the discrepancy between semantic and keyword retrieval to gauge problem complexity, thereby selecting the most suitable retrieval approach and filtering context dynamically. Experiments show that CoAL‑RAG outperforms baseline models on Chinese legal benchmarks (SocialLawQA, LawBench) with a 42.5% BLEU improvement and 3.6× ROUGE‑L, while also achieving strong cross‑jurisdictional performance on English datasets (LexGLUE, CaseHold).
By Jin Su, Zhuofeng Zhao, Huanhuan Wang, Hao Chen
The paper introduces HMS‑SCP, a hierarchical multi‑scale semantic‑aware cooperative perception framework for V2X communication. It uses a spatial importance predictor to select task‑relevant grid elements at multiple scales and maps them directly into complex‑valued symbols for joint source‑channel coding, achieving ultra‑low symbol rates and noise resilience. Experiments on OPV2V and DAIR‑V2X show that HMS‑SCP maintains high‑confidence far‑field detection with sub‑16 ms latency even under severe Rayleigh fading and extreme compression.
By Chun-Yeow Yeoh, Chee Keong Tan, Joanne Mun-Yee Lim, Heng-Siong Lim
QuantumNovelty is an open‑source, skill‑orchestrating language agent that both creates quantum‑computing artifacts—such as papers, ansatz candidates, and patent drafts—and evaluates them through simulated referee and patent‑examiner panels. Its core innovation is an audit‑and‑falsify layer of deterministic gates (Pareto domination, numerical recomputation, Wilson intervals, and cross‑vendor consensus) that restricts claims to those that survive rigorous checks, with every model call logged for transparency. In initial tests on a planted adversarial corpus and a small real‑world deployment, the system successfully flagged all overclaims without false positives and produced panels that were more conservative than typical public acceptance rates.
By Shlomo Kashani
The paper introduces Fair-ASR, a protocol for evaluating black‑box jailbreak attacks using a shared target‑call budget, addressing the bias of prior studies that rely solely on attack success rate. Re‑evaluating 11 attacks under this protocol shows significant shifts in rankings and highlights that many methods are not efficient in both target and attacker calls. The authors then present ReCode, a budget‑efficient attack that combines desensitization rewriting with low‑cost primitives, achieving 85% ASR on GPT‑5 with only 7.19 attacker calls per request under a 20‑target‑call budget.
By Zhida He, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Peng Yu, Jiajia Li, Chaochao Lu, Qiaosheng Zhang
The study investigates how software developers, architects, and AI practitioners select and integrate Large Language Models (LLMs) into modern software systems. Interviews with 22 professionals reveal that functional criteria—such as performance, accuracy, cost, and specific features—dominate model choice, while security concerns are rarely considered. The research highlights a pervasive neglect of established software supply‑chain security lessons, leading to vulnerabilities like malicious components, data leakage, and unintended behavior, and offers actionable recommendations for a proactive, security‑by‑design approach.
By Mahzabin Tamanna, Elizabeth Lin, Sparsha Gowda, Laurie Williams, Dominik Wermke
The paper introduces LeakGauge, a method that appends a suffix to a model’s input to gauge the risk of context leakage before decoding. By mapping prefill token probabilities to an attack‑risk score, LeakGauge achieves high AUROC (0.944–0.996) across 11 large language models, including GLM‑5.2 and Kimi‑K3, and remains robust to language changes and different attack styles. The approach also demonstrates sensitivity to internal leakage directions and can be implemented with fewer than 0.5K additional parameters and minimal latency.
By Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu
The paper introduces PACE (Policy‑Attested Contract Execution), a framework that sits between large‑language‑model (LLM) based autonomous AI agents and on‑chain DeFi operations. PACE defines typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind an approved intent, policy, and simulation report to the exact on‑chain execution bytes, providing replay and expiration protection. In evaluations across 40 tasks and six baselines, PACE achieves zero unsafe executions and zero false positives, outperforming unguarded agents by a large margin.
By Rabimba Karanjai (Larry), Yang Lu (Larry), Richard Williamson (Larry), Hemanth Hm (Larry), Prakhar Mehrotra (Larry), Lei Xu (Larry), Weidong (Larry), Shi
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
By Yiming Du, Yuxin Jiang, Tao Yuan, Jianbo Dai, Shaowei Wang, Jierun Chen, Chaofan Tao, Xianzhi Yu, Lifeng Shang, Kam-Fai Wong, Xiaohui Li, Haoli Bai
MITRE‑SAGE is a multi‑agent retrieval‑augmented generation framework that combines semantic and structural cybersecurity knowledge to enhance large language model question‑answering. It decomposes tasks into query interpretation, evidence retrieval, and answer synthesis, supporting vulnerability assessment, threat profiling, and relationship extraction. Experiments show that MITRE‑SAGE outperforms standalone LLMs and conventional RAG methods, with a lightweight Qwen2.5‑based configuration excelling on most benchmark tasks.
By Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi Atani
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
By Zongyang Qiu, Yihan Wu, Kaixuan Fan, Bo Li, Hui Xiong
The paper presents dynamic shields for AI-controlled autonomous systems, enabling runtime safety enforcement that adapts to changing safety specifications without recomputing from scratch. Unlike traditional static shields, these dynamic shields are pre-designed for a set of possible safety parameters and can quickly adjust as the true specification becomes known during operation. Experiments on robot navigation in unknown terrains show that dynamic shields require only a few minutes offline and a fraction of a second to a few seconds online, outperforming brute-force recomputation by up to five times.
By Davide Corsi, Kaushik Mallik, Andoni Rodriguez, Cesar Sanchez
MobileWorldSafety is a benchmark that evaluates the safety of large language model–powered GUI agents on Android by exposing them to 142 real-world risk tasks involving environmental injection attacks. The benchmark uses a two‑stage verification pipeline—rule‑based checks for clear cases and an LLM judge for ambiguous ones—to distinguish safety failures from capability failures. Experiments on six agents show high vulnerability, with attack success rates between 40.4% and 66.9%, highlighting that current agents often fail to remain safe when faced with adversarial content presented as normal mobile context.
By Sujin Chen, Lijun Li, Tianyi Du, Jing Shao