cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5178, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
Decompose, Don't Expand: Capability-Independent AI Systems by Construction
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.38144v1 Announce Type: new Abstract: A recurring design choice in building AI systems is whether, when a task is too hard for a model, to expand the model (make it larger, better-prompted, fine-tuned), or to decompose the task (extract the parts that admit a determini…

🅲 hạng C
20
BridgeRouter: Gain-Aware Instance Routing over Cross-Modal Bridge Portfolios
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.38152v1 Announce Type: new Abstract: Lightweight representation bridges make pretrained, task-adapted EEG foundation models executable on other biosignal modalities without retraining their backbones. However, selecting a single bridge pathway globally assigns every i…

🅲 hạng C
20
Verification-Guided Retrosynthesis: Reaction Feedback and Evidence Timing
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.38245v1 Announce Type: new Abstract: Retrosynthesis planning seeks synthesis routes from purchasable starting materials to a target molecule. Search over predicted reactions can connect a target to available materials, yet an infeasible reaction can invalidate the res…

🅲 hạng C
20
FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.37722v1 Announce Type: new Abstract: Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery …

🅲 hạng C
20
TensorBound: Characterizing Tensor Binding Failures in AI Compiler and Runtime Stacks
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.37838v1 Announce Type: new Abstract: AI compiler and runtime stacks must preserve bindings between tensor values and their operations, storage, and execution state. These bindings can fail while the underlying objects remain present, with symptoms appearing in another…

🅲 hạng C
20
SPARSEBLEED: Bypassing Attribute-Inference Defenses via Sparsity Optimizations
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38110v1 Announce Type: new Abstract: Deep neural networks (DNNs) are widely deployed in safety- and privacy-critical domains such as healthcare and finance, where models are trained on confidential data. This paper presents the first hardware-level attribute-stealing …

🅲 hạng C
20
A Minimally Informed Black-Box Fake-Report Attack on DRL Traffic-Signal Control
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38557v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) traffic-signal controllers may use vehicle-to-infrastructure (V2I) reports, exposing their perception layer to false-data injection. Existing demonstrations typically assume either white-box access…

🅲 hạng C
20
STAR: Scalable TEE-based Anonymous Rate-limiter
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38602v1 Announce Type: new Abstract: Protecting Internet services from attacks such as TLS/HTTP floods requires rate limiting, yet identifying users to enforce these limits can compromise their privacy. Anonymous rate limiting promises to reconcile these goals, but ex…

🅲 hạng C
20
The use of post-quantum cryptography in the automotive context
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38632v1 Announce Type: new Abstract: This study comparatively evaluates post-quantum cryptography (PQC) in automotive communication scenarios, considering the threat posed by quantum algorithms such as Shor's and Grover's algorithms. The simulations use OMNeT++, Veins…

🅲 hạng C
20
Complexity of Differentially Private Selection via Federated APIs
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38789v1 Announce Type: new Abstract: Differential privacy (DP) has become the standard for privacy-preserving data analysis, yet its practical implementation in federated or distributed settings often faces a significant utility gap compared to the central model. Whil…

🅲 hạng C
20
Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.38793v1 Announce Type: new Abstract: Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development across cloud-edge-IoT systems without fully centralizing raw data. However, distri…

🅲 hạng C
20
Usable String Matching by Humans through Overlaid Presentation
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.39084v1 Announce Type: new Abstract: We explore the ability of humans to compare strings, an error-prone activity which occurs in critical contexts (e.g., bank wire transfers), where it is not always possible to trust a machine to help. We hypothesize that understan…

🅲 hạng C
20
DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.39132v1 Announce Type: new Abstract: Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly. Blockchain-powered federated learning (BCFL) offers a secure and privacy-preserving paradig…

🅲 hạng C
20
Beyond Plausible Prediction: Safety Sufficiency in Web World Models
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40798v1 Announce Type: new Abstract: Web world models increasingly predict the consequences of candidate actions before agents act, yet a plausible predicted future does not necessarily support the correct safety decision. In a matched human evaluation of 3,000 predic…

🅲 hạng C
20
Circumventing the Computational Hardness of Computational Arbitrage
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40831v1 Announce Type: new Abstract: AI model marketplaces host providers with heterogeneous costs and capabilities. These differences create an opportunity for computational arbitrage (Olmedo et al., 2026), in which an intermediary purchases inference from a portfoli…

🅲 hạng C
20
Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science?
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40906v1 Announce Type: new Abstract: Recent scientific agents build knowledge recursively by retrieving evidence, constructing an intermediate state, and judging whether that state contains sufficient information. These agents are evaluated end-to-end, usually without…

🅲 hạng C
20
DiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40938v1 Announce Type: new Abstract: Using customer conversations to train and evaluate financial language models raises confidentiality concerns because non-public financial facts can remain after direct identifiers are masked. Synthetic transcripts offer an alternat…

🅲 hạng C
20
Benchmarking Forecasting Agents on Yesterday's Tomorrows
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40940v1 Announce Type: new Abstract: Digital agents can now gather and organize information, reason over it, and use tools to complete complex tasks. Forecasting puts all of these abilities to the test: it requires integrating incomplete evidence, inferring causal dri…

🅲 hạng C
20
The psychophysics of affect in large language models
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.40985v1 Announce Type: new Abstract: Good decisions often require considering how outcomes will feel. Yet large language models (LLMs) increasingly enter decision workflows, despite little being known about how they map outcomes to feelings or use those mappings in ch…

🅲 hạng C
20
Verifying Text-to-SQL Queries under Changing Business Semantics
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2610.41090v1 Announce Type: new Abstract: In text-to-SQL and AI-agent analytics, successful SQL execution does not establish semantic correctness under changing business definitions. We study revalidation of fixed queries after changes to refund attribution, tax treatment,…

🅲 hạng C