saffron

Saffron-1: Inference Scaling for LLM Safety Assurance 📖 Paper 🛠️ Dependencies The code was tested under the following dependencies: 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...

Important: Red Hat Security Advisory: Red Hat AI Inference 3.4.6 (rocm)

Red Hat AI Inference 3.4.6 rocm is now available. Red Hat AI Inference...

Important: Red Hat Security Advisory: Red Hat AI Inference 3.4.6 (cuda)

Red Hat AI Inference 3.4.6 cuda is now available. Red Hat AI Inference...

Important: Red Hat Security Advisory: Red Hat AI Inference Model Optimization Tools 3.4.6 (cuda)

Red Hat AI Inference Model Optimization Tools 3.4.6 cuda is now available. Red Hat AI Inference Model Optimization Tools...

Important: Red Hat Security Advisory: Red Hat AI Inference 3.4.6 (spyre)

Red Hat AI Inference 3.4.6 spyre is now available. Red Hat AI Inference...

Important: Red Hat Security Advisory: Red Hat AI Inference 3.4.6 (cpu)

Red Hat AI Inference 3.4.6 cpu is now available. Red Hat AI Inference...

FLock.io Unveils Edge Decision Model, Built on Qwen, for Enhanced Data Privacy

Built on Qwen3.5-2B, the System One model executes sub-31ms local inference, allowing enterprises to run automated classifications quickly, at low cost and completely offline without transmitting sensitive data to third-party cloud servers...

awesome-latency-attacks

Awesome Deep Learning Latency Attacks & Defenses This repository is maintained as a companion resource for the survey “Deep Learning Latency Attacks and Defenses: A Cross-Domain Survey.” It indexes papers, code links, taxonomy notes, and figures on latency-oriented availability threats in deploye...

Oihk-pentesting

OIHK-pentesting OIHK-pentesting is an autonomous multi-agent engine for authorized security assessments. A root planner delegates to recon, discovery, attack Privesc, validation, and reporting agents — and the engine itself enforces scope, egress, evidence, and resource policy no matter which mod...

Critical: Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (cpu)

Red Hat AI Inference 3.5.2 cpu is now available. Red Hat AI Inference...

Critical: Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (spyre)

Red Hat AI Inference 3.5.2 spyre is now available. Red Hat AI Inference...

Critical: Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (cuda)

Red Hat AI Inference 3.5.2 cuda is now available. Red Hat AI Inference...

CVE-2026-65104

NVIDIA Megatron-LM for all platforms contains a vulnerability in inference, where an attacker could cause hash collisions in the cache used for inference requests. A successful exploit of this vulnerability might lead to data tampering and partial information disclosure...

CVE-2026-65104

The NVIDIA Megatron-LM framework for all platforms contains a vulnerability within its inference component. The root cause is the use of weak hashes (CWE-328), which allows an attacker to trigger hash collisions in the cache used for inference requests. Exploitation of this flaw could result in d...

CVE-2026-24207

CVE-2026-24207 — NVIDIA Triton SageMaker Auth Bypass to Unauth RCE Unauthenticated attackers can reach the model-management surface of NVIDIA Triton Inference Server on the SageMaker and Vertex AI HTTP ports — bypassing the operator's --http-restricted-api configuration. Combined with the SageMak...

Important: Red Hat Security Advisory: Red Hat AI Inference Model Optimization Tools 3.5.2 (CUDA)

Red Hat AI Inference Model Optimization Tools 3.5.2 CUDA is now available. Red Hat AI Inference Model Optimization Tools...

Critical: Red Hat Security Advisory: Red Hat AI Inference Tech Preview 3.5.2 (Gaudi)

Red Hat AI Inference Tech Preview 3.5.2 Gaudi is now available. Red Hat AI Inference Tech Preview...

Critical: Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (ROCm)

Red Hat AI Inference 3.5.2 ROCm is now available. Red Hat AI Inference...

PrivacyRaven

Note: This project is on hiatus. PrivacyRaven is a privacy testing library for deep learning systems. You can use it to determine the susceptibility of a model to different privacy attacks; evaluate privacy preserving machine learning techniques; develop novel privacy metrics and attacks; and...

gradient-untangler

gradient-untangler A local research harness that searches for the exact tokens that make an open-weight language model start its answer the way you specify. Open-weight models ship as ordinary files: config.json, a tokenizer, and one or more .safetensors or .bin shards. A Hugging Face id is only ...