spectre-attack-demo

Spectre 攻击示例 使用2018年1月2日披露的“Spectre”漏洞（CVE-2017-5753和CVE-2017-5715）的示例 Spectre打破了不同应用程序之间的隔离。它允许攻击者欺骗那些遵循最佳实践的无错误程序，使其泄露秘密。事实上，这些最佳实践的安全检查反而增加了攻击面，并可能使应用程序更容易受到Spectre攻击。 Spectre paper - Spectre论文及代码来源 语言 C语言，使用库： stdio.h stdlib.h stdint.h intrin.h - 用于 rdtscp 和 clflush 示例的作用是什么？ 我们在内存中放入文本 “The...

cve-2017-5753

CVE-2017-5753 CVE-2017-5753, Spectre, PoC, C, ASM para OSX, MAC, Intel Arch Compilar: gcc -o a.out spectre.c Salida: 0x41414141 También se agregó la salida de Control Flow desde Hopper.app para Aprendices Visuales Puedes ajustar el tamaño de basura y obtener lecturas más confiables Dependiendo de...

spectre-attack

Spectre 攻击示例 使用 2018 年 1 月 2 日披露的“Spectre”漏洞利用的示例（CVE-2017-5753 和 CVE-2017-5715） Spectre 打破了不同应用程序之间的隔离。它允许攻击者诱骗遵循最佳实践的无错误程序泄露其秘密。事实上，这些最佳实践的安全性检查反而增加了攻击面，并可能使应用程序更容易受到 Spectre 攻击。 Spectre 论文 - Spectre 论文及代码来源 语言 C 语言，使用以下库： stdio.h stdint.h intrin.h - 用于 rdtscp 和 clflush 示例的功能是什么？ 我们将文本 "The...

retbleed-speculative-execution-poc

Retbleed: Ejecución Arbitraria de Código Especulativo mediante Desbordamiento del RSB Una reproducción práctica de Retbleed CVE-2022-29900 / CVE-2022-29901 — el ataque microarquitectónico de 2022 que rompió la defensa "Retpoline" al demostrar que las instrucciones ret, consideradas seguras durant...

Astra Linux – Vulnerability in gnupg1

Libgcrypt before version 1.7.8 is vulnerable to a cache-side-channel attack that can lead to a complete failure of the RSA-1024 algorithm. This attack occurs when the left-to-right method is used for computing the sliding-window expansion. It is believed that the same attack also works on the...

ROS-20260819-73-0075

The vulnerability in Python-Django relates to the exposure of information through caching. Exploiting this vulnerability allows an attacker to gain access to the memory of a supervisor machine or other virtual machines. This can be achieved by implementing attacks through secondary channels,...

Exploit for Observable Discrepancy in Intel Atom_C

🛡️ Spectre Variant 2 CVE-2017-5715 — Hardware Vulnerability...

MiracleLinux 3 : libgcrypt-1.4.4-7.AXS3 (AXSA:2013-678:01)

The remote MiracleLinux 3 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2013-678:01 advisory. Libgcrypt is a general purpose crypto library based on the code used in GNU Privacy Guard. This is a development version. Security issues fixed with this...

MiracleLinux 4 : libgcrypt-1.4.5-11.AXS4 (AXSA:2014-002:01)

The remote MiracleLinux 4 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2014-002:01 advisory. Libgcrypt is a general purpose crypto library based on the code used in GNU Privacy Guard. This is a development version. Security issues fixed with this...

EUVD-2025-202587

XiangShan Nanhu V2 and XiangShan Kunmighu V3 were discovered to use speculative execution and indirect branch prediction, allowing attackers to access sensitive information via side-channel analysis of the data cache...

CVE-2025-63094

XiangShan Nanhu V2 and XiangShan Kunmighu V3 were discovered to use speculative execution and indirect branch prediction, allowing attackers to access sensitive information via side-channel analysis of the data cache...

EUVD-2013-4146

Malware in sbrugna...

EUVD-2018-4410

Malware in sbrugna...

EUVD-2018-4406

Malware in sbrugna...

EUVD-2017-16542

Malware in sbrugna...

EUVD-2018-2915

Malware in sbrugna...

EUVD-2016-7411

Malware in sbrugna...

EUVD-2014-0168

Malware in sbrugna...

Linux Distros Unpatched Vulnerability : CVE-2017-14737

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - A cryptographic cache-based side channel in the RSA implementation in Botan before 1.10.17, and 1.11.x and 2.x before 2.3.0, allows a local attacker to recover...

Spill the Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models LLMs. In this work, we introduce Spill The Beans, a novel application of cache side-channels to leak tokens generated by an LLM. By co-locating an attack...