cập nhật 37 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5180, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
Developing Security Metrics for Automated Compliance Checking
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32690v1 Announce Type: new Abstract: To automatically check for compliance with security-related standards, prose requirements must be translated to technical properties to make them measurable. A multitude of metrics have been proposed in past literature, but they ar…

🅲 hạng C
20
EVSEFuzz : A Tool for Automated Testing of Protocol Implementations
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32902v1 Announce Type: new Abstract: The rapid adoption and development of electric vehicle (EV) networks has required the expansive deployment of EV charging infrastructure (EVCI) which relies on communication protocols such as the open charge point protocol (OCPP) t…

🅲 hạng C
20
The Entire Quantum Computer on a Classical Leash
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.31775v1 Announce Type: cross Abstract: We show that a classical client with no quantum hardware can use a single untrusted and potentially malicious quantum server as if it were its own trusted quantum computer. Through the server, the client can privately choose and …

🅲 hạng C
20
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32059v1 Announce Type: cross Abstract: Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content, motivating machine unlearning (MU) to selectively remove target concepts while preserving general capabilit…

🅲 hạng C
20
Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32182v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorly understood. We present a lightweight inference-time framework for localizing and manipulating safety-sensit…

🅲 hạng C
20
Iterative Behavioral Identification for Covert Misappropriation Attacks
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32662v1 Announce Type: cross Abstract: We present a data-driven, three-phase framework for covert misappropriation attacks on closed-loop networked control systems. A man-in-the-middle (MITM) adversary, with access only to intercepted input-output data, incrementally …

🅲 hạng C
20
Quantum Cadence: Post-Quantum Consensus with Multiple Concurrent Proposers
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32803v1 Announce Type: cross Abstract: The consensus protocols of most high-performance blockchains use quorum certificates, which bundle the signatures of a quorum of validators. Signature schemes such as BLS can aggregate the signatures of a whole quorum into a sing…

🅲 hạng C
20
Differential Fault Analysis of Lilliput under Random-Location Nibble Faults
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2603.19781v3 Announce Type: replace Abstract: Lilliput is a lightweight block cipher based on a Type-2 Extended Generalized Feistel Network (EGFN). Although it has been studied under conventional cryptanalytic techniques, its resistance to fault attacks remains largely une…

🅲 hạng C
20
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning
📄 Paper HF Daily Papers 29 ngày trước

Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction, imbalanced difficulty, and cross-domain interference. We introduce MMVistaReaso…

🅲 hạng C
20
Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization
📄 Paper HF Daily Papers 29 ngày trước

Scaling embedding capacity alongside Transformer computation is an emerging trend in language models. This trend makes high compression rates increasingly useful. Hence, we study extreme compression of Per-Layer Embeddings (PLE), which follow this trend and account for 35.2% of t…

🅲 hạng C
20
Hidden Backdoor Attack on Deep Contrastive Clustering
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.33116v1 Announce Type: new Abstract: Deep contrastive clustering has become a representative paradigm for unsupervised image clustering, yet its security under training-time poisoning remains largely unexplored. This paper investigates a hidden backdoor threat against…

🅲 hạng C
20
A-GE: Privacy-Preserving Age Assurance via Fine-Grained Motion
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.33206v1 Announce Type: new Abstract: Age assurance faces a fundamental privacy dilemma: meaningful assurance typically requires revealing identity or other sensitive information, whereas privacy-preserving alternatives often provide little assurance. Existing approach…

🅲 hạng C
20
Secure and Functional Code Generation with Self-Evaluation
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.33450v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate functionally correct code that remains insecure. Security-focused fine-tuning can be expensive and is not always available, motivating inference-time approaches. Security-oriented prompting…

🅲 hạng C
20
CVM-Store: A Secure Storage System for Confidential Virtual Machines
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.34560v1 Announce Type: new Abstract: Stateful cloud workloads require high-performance persistent storage when running on untrusted cloud infrastructure. Confidential Virtual Machines (CVMs) promise to protect these workloads through hardware-enforced memory encryptio…

🅲 hạng C
20
Compound Environmental Operating Stress and Cyber-Induced Pump Disruption in Water Distribution Networks: Matched Hydraulic Impacts, Service Continuity, and Sustained Recovery
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.34670v1 Announce Type: new Abstract: Digitally controlled water distribution systems must maintain service during disruptions, yet restoring water delivery does not necessarily ensure hydraulic recovery. This study evaluates cyber-induced pump outages under hypothetic…

🅲 hạng C
20
Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking
📄 Paper arXiv cs.CR 23 ngày trước

arXiv:2610.34942v1 Announce Type: new Abstract: Hyperdimensional computing (HDC) offers efficient learning and inference for resource-constrained systems, yet ownership verification of its models remains underexplored. We present the first systematic investigation of model water…

🅲 hạng C
20
Nested Sparsity for Scalable Pretraining and Continual Learning
📄 Paper HF Daily Papers 29 ngày trước

Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional computation: only a sparse subset of model weights is used in each forward pass. In MoE transformers, this sparsity arises in the MoE operator, which generalizes …

🅲 hạng C
20
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
📄 Paper HF Daily Papers 25 ngày trước

A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers. This paper examines whether models are self-attributive: that is, whether they indicate when -- and only when -- their responses to questions ar…

🅲 hạng C
20
Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding
📄 Paper HF Daily Papers 25 ngày trước

Image and video generators can produce spatially consistent visual content, but how to use this capability to improve spatial understanding remains underexplored. We study this problem from two perspectives: geometric supervision during training and explicit geometric evidence du…

🅲 hạng C
20
Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33103v1 Announce Type: new Abstract: Prospect theory splits risky choice into three parts: loss aversion, measured by the relative weight of losses to gains, $\lambda$ (e.g., $\lambda = 2$ implies that losses weigh twice as much as gains), diminishing sensitivity to t…

🅲 hạng C
20
Conformance as a Distribution: Delegation Contracts, Error Budgets, and the Allocation of Evaluation Authority in Use-Based AI Regulation
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33112v1 Announce Type: new Abstract: Use-based AI regulation assigns obligations by deployment risk but lacks an evidentiary object to carry them. A benchmark score is a property of a model; conformance of a deployment is a failure rate under a declared distribution o…

🅲 hạng C
20
Optimal Correction Sets for Provable Redress of Contestable Causal Discovery
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33138v1 Announce Type: new Abstract: Constraint-based causal discovery relies on conditional-independence (CI) tests that may conflict in finite samples, leaving no causal graph that satisfies them all. Causal Assumption-based Argumentation (ABA) makes these tests exp…

🅲 hạng C
20
Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33200v1 Announce Type: new Abstract: Current sign language recognition and translation benchmarks are commonly collected in controlled settings using fixed or studio-style cameras, particularly limiting their ability to reflect how signers communicate in everyday mobi…

🅲 hạng C
20
Scaling Qualitative Analysis with Large Language Models: Development and Validation of the Smart Coder Framework for Human-LLM Collaborative Coding
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33205v1 Announce Type: new Abstract: Current uses of large language models (LLMs) for qualitative coding often rely on ad hoc prompting with limited guidance for reliability and human oversight. To address these limitations, we propose the Smart Coder Framework, a thr…

🅲 hạng C