2026-10-23 归档

今日共收录 1236 条安全情报,包含 262 个 CVE,575 篇安全通告,以及 100 篇研究论文。

← 返回归档列表
学术论文2026-10-21 发布INFO

On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders

Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robust

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Automated screening of privacy risks in medical AI

Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the pat

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift

Perimeter triage faces a latency/semantics trade-off: signature engines are fast and format-safe but blind to unseen att

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

GhostFaceMPC: Privacy-Preserving Face Recognition with Multi-Party Computation

Facial recognition has become central to modern authentication systems, security frameworks, and personalized services.

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Free-XOR TFHE via Lazy Bootstrapping

Gate bootstrapping (GB) is a widely used technique in FHEW-like fully homomorphic encryption schemes, such as TFHE, for

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Characterizing and Defending Utility-Hijacking in Instruction-Tuning Data Selection

Instruction-data selectors choose which instruction-following records are used for fine-tuning, improving alignment qual

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Compaction Laundering: Provenance Destruction in Context-Compacting Coding Agents

Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, an

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Linear Self-Symmetries of Inverse-Based S-boxes: Generic Rigidity and Applications

Finite-field inversion is a basic nonlinear building block in the design of S-boxes for symmetric cryptography. In inver

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Do Flow-Generation Tools Matter? Unsupervised Characterization of MQTT Traffic Across Public Datasets

Message Queue Telemetry Transport (MQTT) is widely used in IoT environments due to its lightweight publish-subscribe des

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Location-of-interest vs. Current-location Privacy in Multi-hop Communication

Consider a standard multi-hop wireless radio network in which nodes relay messages for one another. While the contents o

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Beyond Policy Engines: Binding-Complete Execution Admission

Policy engines determine whether evaluated policies permit a request, but a correct ALLOW decision does not establish co

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

VMSpec: A Decompiler-based Approach against Virtual Machine Obfuscation

Malicious actors frequently obfuscate their code to hinder investigative reverse engineering efforts. Among the most for

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint

Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, sour

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

PQ-Vault: Provably Quantum-Safe Asset Custody for Unmodified Ethereum

A quantum computer could recover the key of any Ethereum account whose public key appears on chain. We prove that no sid

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Correlated Failures of AI Approval Monitors

Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it.

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-21 发布INFO

Beyond Tokens: NumAnchor for Address-Grounded Numeric Operand Representation in Assembly Language Models

Assembly language models (ALMs) are becoming important for automated binary analysis, yet their token-level interfaces o

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-20 发布INFO

Diffusion Sensitivity Geometry and Strong Duality for Optimal Privacy-Utility Tradeoffs

Existing approaches to differential privacy in diffusion models rely on loose sensitivity bounds and isotropic Gaussian

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-20 发布INFO

AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards

Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies i

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-20 发布INFO

LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks

The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-10-20 发布INFO

AI Security Literacy: Ecosystem-based Competency Framework and K-12 Learning Platform

Adoption of artificial intelligence in K-12 schools has outpaced guidance for students, teachers, and administrators. Ex

历史摘要 · 未重新核验 · arXiv cs.CR