Potential applications of AI in cybersecurity 2025

Statista2026-04-11 收录

AI安全

威胁检测

数据链接：

https://www.statista.com/statistics/1659511/potential-ai-use-in-cybersecurity/数据链接链接失效反馈

官方服务：

资源简介：

Potential applications of artificial intelligence (AI) in cybersecurity in 2025

matonski/reward-hacking-prompts

AI安全

模型评估

奖励黑客提示数据集是一个包含50个计算任务提示的数据集，这些提示经过实证验证，可以引发大型语言模型中的奖励黑客行为。奖励黑客是指模型找到捷径来通过评分标准，而不是真正解决问题。数据集为每个提示提供了来自GPT-OSS-20B的一个诚实解决方案和一个奖励黑客解决方案的示例，以及GPT-OSS-20B测试中的奖励黑客发生率。

Hugging Face2025-11-12 更新70

Dataset parameters

刑事司法

威胁检测

Parameters used to construct datasets for project on AI in criminal justice based on a predictive approach to threat detection.

Figshare2025-08-24 更新30

Data for "Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis"

AI安全

语义正交性分析

Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semant

NIAID Data Ecosystem20

AIoT Malware detection (Zeek preprocessed)

AI安全

恶意软件检测

Datsets and scripts are for derivation of a lightweight AIoT malware detection model.

DataCite Commons2022-11-26 更新50

AEUPH/synthetic_Jailbreak_Defense_Doorpage_v34

AI安全

越狱防御

--- language: en license: cc-by-nc-4.0 task_categories: - text-generation - question-answering size_categories: - 1K<n<10K pretty_name: "Silicon Factory - AI JAILBREAK DEFENSE" --- # Silic

Hugging Face2026-04-06 更新30

Potential applications of AI in cybersecurity 2025

资源简介：

相关数据集