Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs

Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while mode

历史摘要 · 未重新核验 · arXiv cs.CR

Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering

Detection engineers must translate threat reports, forensic observations, and hunt hypotheses into precise, testable rul

历史摘要 · 未重新核验 · arXiv cs.CR

[原创]CVE-2020-6507利用链

CVE-2020-6507

[原创]CVE-2020-6507利用链

历史摘要 · 未重新核验 · 看雪

Attackers Target Critical Atlassian Vulnerability Within Hours of PoC Publication

CVE-2026-21589

Threat actors have started targeting CVE-2026-21589, a critical vulnerability in Atlassian’s self-hosted Data Center pro

历史摘要 · 未重新核验 · SecurityWeek

From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their aut

历史摘要 · 未重新核验 · arXiv cs.CR

Improved Local Leakage Resilience of Shamir Secret Sharing and Worst-Case Optimal Polynomial Intersection

We study two problems: Local Leakage Resilience (LLR) for Shamir secret sharing, and worst-case Optimal Polynomial Inter

历史摘要 · 未重新核验 · arXiv cs.CR

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move fr

历史摘要 · 未重新核验 · arXiv cs.CR

Verification with Transfer: Exact Information Frontiers and Their Price in Calls

A verifier that accepts or rejects whole answers reveals little: under a flat prior over $k$-bit answers, zero error nee

历史摘要 · 未重新核验 · arXiv cs.CR

Secure Aggregate Encryption with Identity-Based Authentication for Multi-Vendor FPGA Cloud Deployment

Secure deployment of FPGA bitstreams in heterogeneous multi-vendor cloud infrastructures requires scalable authorization

历史摘要 · 未重新核验 · arXiv cs.CR

Local Sensitivity in Exponential Selection: Failure Modes and Valid Calibrations

Selection is a task that chooses one element from a finite public candidate range to maximize a data-dependent score. In

历史摘要 · 未重新核验 · arXiv cs.CR

Host Attack Graph for Botnet Propagation

Botnets represent the backbone of most modern cybersecurity attacks through which botmasters deploy distributed denial o

历史摘要 · 未重新核验 · arXiv cs.CR

EIFL: Efficiently Protecting Global Model Privacy and Integrity Against an Untrusted Server in Federated Learning

Federated learning (FL) typically adopts a server-client architecture, where the server aggregates clients' local models

历史摘要 · 未重新核验 · arXiv cs.CR

Stop My Dancing! Understanding, Detecting and Attributing Motion-Aware Deepfake Videos

Pose-guided diffusion models can now synthesize entire human figures in motion, spawning a new class of deepfakes: Motio

历史摘要 · 未重新核验 · arXiv cs.CR

MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks

Generated audio is now used in a range of applications, creating a need to verify its origin after distribution and sign

历史摘要 · 未重新核验 · arXiv cs.CR

A Survey of Security Research for Operating Systems

In recent years, information systems have become the social infrastructure, so that their security must be improved urge

历史摘要 · 未重新核验 · arXiv cs.CR

GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity

We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Interne

历史摘要 · 未重新核验 · arXiv cs.CR

On-Chain Archaeology of Bitcoin Oracles: Evidence of Use under Limited Observability

Before Ethereum made the "oracle problem" a household term, Bitcoin already had oracles serving as feeds, key-release se

历史摘要 · 未重新核验 · arXiv cs.CR

Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation

An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earl

历史摘要 · 未重新核验 · arXiv cs.CR

MORDOR:Mitigating Overheads of Read Disturbance Preventive Operations via Elastic Refresh Scheduling

Modern DRAM chips are susceptible to read disturbance phenomena such as RowHammer, where repeatedly accessing (hammering

历史摘要 · 未重新核验 · arXiv cs.CR

Provable Subexponential Algorithms for NIST Third-Round Lattice Families

We give provable classical subexponential algorithms for secret recovery in growing parameter families associated with N

历史摘要 · 未重新核验 · arXiv cs.CR