Privacy Conductor: An Architectural Enforcement of Contextual Integrity in LLM-Based Document Retrieval

Large language model (LLM) that retrieve internal documents within an organization must decide who may receive them. Exi

历史摘要 · 未重新核验 · arXiv cs.CR

LLM-based Code Auditing by Inferring and Evaluating Developer Assumptions

When we see a null pointer check, we know that the developer believes that the pointer may not be initialized. If the sa

历史摘要 · 未重新核验 · arXiv cs.CR

Security in LLM-Assisted Coding: A Systematic Literature Review

Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic rev

历史摘要 · 未重新核验 · arXiv cs.CR

Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models

Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in whi

历史摘要 · 未重新核验 · arXiv cs.CR

[原创]IDAPro v9.4.260714 汉化补丁修正错误

[原创]IDAPro v9.4.260714 汉化补丁修正错误

历史摘要 · 未重新核验 · 看雪

Microsoft Security Advisory CVE-2026-92707 - ASP.NET Core Denial of Service Vulnerability

## Executive summary Microsoft is releasing this security advisory to provide information about a vulnerability in Micr

历史摘要 · 未重新核验 · GitHub Advisory

[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

CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报

CVE-2026-39821

CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报

历史摘要 · 未重新核验 · 先知社区

AegisAsync: Symbolic Async-Event Simulation for Risks in Python Asynchronous Programs

Security and robustness risks in Python async programs depend on event order, object identity, and execution after excep

历史摘要 · 未重新核验 · arXiv cs.CR

$\mathsf{EFI}\Leftrightarrow\mathsf{1PRS}$

A series of recent works has established EFI pairs as the "minimal" assumption for quantum cryptography. Recently, Caval

历史摘要 · 未重新核验 · arXiv cs.CR

Dynamic Attack Surfaces: A Queue of Branching Processes

Modern attack surfaces are inherently dynamic. Vulnerabilities emerge over time and they remain exposed to exploit until

历史摘要 · 未重新核验 · arXiv cs.CR

ARACDE: Retrofitting Databases with ABAC using External Authorization Engines

This paper proposes a methodology for decoupling the authorization logic of a relational database from its core data man

历史摘要 · 未重新核验 · arXiv cs.CR

Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications

System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structure

历史摘要 · 未重新核验 · arXiv cs.CR

DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization

Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), ye

历史摘要 · 未重新核验 · arXiv cs.CR

Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence

This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emul

历史摘要 · 未重新核验 · arXiv cs.CR

X.js: A Live Benchmark for Node.js Taint-Style Vulnerabilities

JavaScript vulnerabilities in npm packages pose a significant risk to the Node.js ecosystem, and a growing body of work

历史摘要 · 未重新核验 · arXiv cs.CR

Prompt-Segmentation Meets ROI Encryption: Fine-Grained Video Protection Based on Diffusion Isolation

Region-of-interest (ROI) selective encryption in H.265/HEVC aims to protect sensitive content while preserving the utili

历史摘要 · 未重新核验 · arXiv cs.CR

Tanchun: Robust Flow-Based HTTP(S) DDoS Detection via Behavioral Attribute Guidance

HTTP(S) DDoS attacks have surged in frequency and scale, posing a significant threat to network security. Flow-based det

历史摘要 · 未重新核验 · arXiv cs.CR

HULK: An Efficient Algorithm for Enabling Fast Bulk Bitwise Operations on Homomorphically Encrypted Data

A wide range of important cloud applications, e.g., database analytics, graph analytics, and genome analysis, spend a co

历史摘要 · 未重新核验 · arXiv cs.CR

Standing, Not Truth: Who May Say What About Whom in Agentic Selection

Software agents increasingly choose on a user's behalf among competing offerings described by the parties who benefit. A

历史摘要 · 未重新核验 · arXiv cs.CR