GuardReasoner-VL

GuardReasoner-VL: Sicherung von VLMs durch verstärktes Reasoning Yue Liu, Shengfang Zhai, Mingzhe Du Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang Xinfeng Li, Kun Wang, Junfeng Fang, Jiaheng Zhang, Bryan Hooi 1National University of Singapore, 2Nanyang Technological University Um die Sicherheit...

meta-ai-support-prompt

Prompt di sistema di Meta AI Support Assistant Prompt di sistema estratto da Meta AI Support Assistant il 1 giugno 2026. File system-prompt.md — Prompt di sistema estratto ⚠️ Disclaimer e Avviso legale Scopo Questo repository è pubblicato esclusivamente per scopi educativi e di ricerca sulla...

xmloxide

xmloxide Una reimplementazione in Rust puro di libxml2 — la libreria di parsing XML/HTML de facto standard nel mondo open-source. libxml2 è diventata ufficialmente non mantenuta a dicembre 2025 con problemi di sicurezza noti. xmloxide punta ad essere un sostituto memory-safe e ad alte prestazioni...

autoguardrails

autoguardrails Open source di Santander AI Lab. Una libreria di ricerca / harness di valutazione per i guardrail LLM / AI-safety in stile autoresearch: cerca su un'unica superficie mutabile policy.md per minimizzare il tasso di successo degli attacchi ASR rispetto a una suite di valutazione fissa...

clr

CLR C ontrollore di L ifetime e altri R affinamenti di tipo per Zig Video: https://www.youtube.com/watch?v=mf0WzTOe-40 Sponsorizza: https://buymeacoffee.com/dnautics discuti su HN: https://news.ycombinator.com/item?id=42923829 discuti su lobste.rs:...

nano-analyzer

Nano-analyzer Uno scanner minimalista per vulnerabilità zero-day basato su LLM, creato daAISLE. Prototipo di ricerca a scopo dimostrativo. Si tratta di un semplice harness a file singolo in grado di rilevare reali vulnerabilità zero-day. Tieni presente che è un prototipo, orientato verso bug di...

safety

!NOTE Kommen Sie zu uns bei SafetyCLI. Wir stellen für verschiedene Positionen ein. Inhaltsverzeichnis Inhaltsverzeichnis Einleitung Hauptfunktionen Erste Schritte GitHub Action Command Line Interface 1. Installation...

GHSA-8C9H-MHQX-6Q3F vulnerabilities

Vulnerabilities for packages: firefox...

delirium-ai-safety-benchmark

Delirium KI-Sicherheits-Benchmark Ein diagnostisches Framework zur Messung der Verwundbarkeit von LLMs gegenüber Affective Contextual Erosion ACE und verwandten liminalen Angriffsvektoren. Delirium ist kein Exploitation-Tool. Es ist ein standardisierter Benchmark, der darauf ausgelegt ist, den...

FreeBSD : FreeBSD -- Multiple vulnerabilities in ppp(8) (204af099-a0ff-11f1-ae1f-bc241121aa0a)

The version of FreeBSD installed on the remote host is prior to tested version. It is, therefore, affected by multiple vulnerabilities as referenced in the 204af099-a0ff-11f1-ae1f-bc241121aa0a advisory. ppp8 contained three memory safety errors in its handling of multilink endpoint discriminator...

CVE-2026-79285

CVE-2026-79285 is an uninitialized resource vulnerability in ANGLE , a graphics library component used by Google Chrome on Windows prior to version 152.0.7977.65 . A remote attacker can exploit it by luring a user to visit a crafted HTML page , enabling cross-origin data disclosure (information d...

safety

!NOTE Come and join us at SafetyCLI. We are hiring for various roles. Table of Contents Table of Contents Introduction Key Features Getting Started GitHub Action Command Line Interface 1. Installation 2. Log In or Register...

FreeBSD -- Multiple vulnerabilities in ppp(8)

Problem Description: ppp8 contained three memory safety errors in its handling of multilink endpoint discriminator options. mpEnddisc used incorrect length calculations when formatting endpoint discriminator addresses for display, allowing a received endpoint option to overflow a global result...

The vulnerability of the f81604_read_int_callback() function in the drivers/crypto/ccp/sev-dev-tsm.c file of the Linux kernel cryptographic accelerator driver allows a attacker to compromise the confidentiality, integrity, and accessibility of protected information.

The vulnerability of the f81604readintcallback function in the drivers/crypto/ccp/sev-dev-tsm.c file of the Linux kernel cryptographic accelerator driver is related to the execution of operations outside of memory buffers. Exploiting this vulnerability could allow an attacker to compromise the...

FreeBSD-SA-26:60.ppp

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 ============================================================================= FreeBSD-SA-26:60.ppp Security Advisory The FreeBSD Project Topic: Multiple vulnerabilities in ppp8 Category: core Module: ppp Announced: 2026-08-25 Credits: Robert Morris...

CVE-2026-74710

A flaw was found in the Linux kernel's AFXDP eXpress Data Path component. This vulnerability arises because the AFXDP mechanism accepts a transmit TX metadata length that is smaller than required, allowing the kernel to read beyond its designated memory area. An attacker could potentially exploit...

tesla-security-research

Ricerca sulla Sicurezza di Tesla Ricerca sulle vulnerabilità del sistema infotainment Tesla Model 3/Y Intel Atom MCU, Linux 4.14.235, divulgata responsabilmente a Tesla tramite Bugcrowd. Ottenuto accesso root persistente su una Tesla Model 3 di produzione tramite una vulnerabilità di command...

saffron

Saffron-1: Scaling dell'inferenza per la garanzia di sicurezza degli LLM 📖 Paper 🛠️ Dipendenze Il codice è stato testato con le seguenti dipendenze: Python 3.12.3 CUDA 12.2 typingextensions==4.14.0 numpy==2.2.6 torch==2.5.1 huggingfacehub==0.30.2 accelerate==1.1.1 datasets==3.1.0 evaluate==0.4.3...

Astra Linux – Vulnerability in Linux 5.15

In the Linux kernel, the following vulnerabilities have been resolved: powerpc/setmemory: Avoid spinlock recursion in changepageattr The commit 1f9ad21c3b38 “powerpc/mm: Implement setmemory routines” included a spinlock call in changepageattr in order to safely perform the three-step operations...

Astra Linux – Vulnerability in Firefox

Mozilla developers Christian Holler and Jason Kratzer reported memory safety bugs in Firefox 95. Some of these bugs exhibited signs of memory corruption, and we believe that with sufficient effort, some of these bugs could have been exploited to execute arbitrary code. This vulnerability affects...