2019 matches found
CVE-2026-112086
A vulnerability was found in ESPnet up to 202610.post2. This affects the function buildmodel of the file espnet3/publication/inferencemodel.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack remotely...
CVE-2026-112086 ESPnet Inference Model inference_model.py build_model deserialization
A vulnerability was found in ESPnet up to 202610.post2. This affects the function buildmodel of the file espnet3/publication/inferencemodel.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack remotely...
CVE-2026-112086 ESPnet Inference Model inference_model.py build_model deserialization
A vulnerability was found in ESPnet up to 202610.post2. This affects the function buildmodel of the file espnet3/publication/inferencemodel.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack remotely...
EUVD-2026-104089
A vulnerability was found in ESPnet up to 202610.post2. This affects the function buildmodel of the file espnet3/publication/inferencemodel.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack remotely...
CVE-2026-112086 ESPnet Inference Model inference_model.py build_model deserialization
A vulnerability was found in ESPnet up to 202610.post2. This affects the function buildmodel of the file espnet3/publication/inferencemodel.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack remotely...
CVE-2026-112086
A vulnerability exists in ESPnet up to version 202610.post2 within the Inference Model Handler component. Specifically, the build_model function in the file espnet3/publication/inference_model.py is susceptible to deserialization due to the manipulation of the _target_ argument. This flaw can be ...
openpcc
OpenPCC OpenPCC is an open-source framework for provably private AI inference, inspired by Apple’s Private Cloud Compute but fully open, auditable, and deployable on your own infrastructure. It allows anyone to run open or custom AI models without exposing prompts, outputs, or logs - enforcing...
PT-2026-117233
A vulnerability was found in ESPnet up to 202610.post2. This affects the function build model of the file espnet3/publication/inference model.py of the component Inference Model Handler. The manipulation of the argument target results in deserialization. It is possible to launch the attack...
vicidial-cve-2024-8503-blind-sqli-poc
vicidial-cve-2024-8503-blind-sqli-poc Unauthenticated time-based blind SQL injection proof of concept for VICIdial's VERMAJAXfunctions.php endpoint CVE-2024-8503. The project is intended for authorized security testing, validation, and education only. Overview CVE-2024-8503 is an unauthenticated...
CVE-2023-43654
CVE-2023-43654 ShellTorch is a chain of 3 Critical Vulnerabilities in PyTorch TorchServe - the default inference server of PyTorch. This is an End-to-End POC for an SSRF vulnerability which leads to Arbitrary Remote Code Execution from the network 1. Run TorchServe 0.8.1 docker run -d --rm -it -p...
Agentic-CLIP-Benchmark
Agentic-CLIP-Benchmark: Zero-Shot Evaluation on CIFAR-10 -green.svg This project implements a robust, automated pipeline for evaluating OpenAI's CLIP ViT-B/32 model on the full CIFAR-10 test set 10,000 images. Developed using an AI Native workflow Trae IDE , it achieves a high-precision zero-shot...
CVE-2026-105038
The EnergizeLab Eilik and EilikO FastAPI AI inference and profiling services expose AI model administration functions without authentication. An unauthenticated remote attacker can change AI model configuration and switch the model in use at runtime...
cve-2026-47627
CVE-2026-47627 — NVIDIA Triton Inference Server Path Traversal → DoS Zip-Slip Writeup lengkap hasil riset & PoC di repo ini image nvcr.io/nvidia/tritonserver:26.05-py3 / server v2.69.0. Repo di-setup untuk selalu explicit agar PoC tanpa restart via gRPC. Daftar Isi 1. Ringkasan CVE 2. Lingkungan...
inference-gateway-PoC
inference-gateway: security advisory | ---|--- Researcher| Dostxodjayev Abdullox @squeeze440 Advisory| GHSA-5293-fcm6-fh8v CVE| CVE-2026-87009 CVSS 3.1| 5.4 Medium — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L Weakness| CWE-352, CWE-306, CWE-346 Status| Fixed in v0.46.0 Summary : inference-gatew...
CVE-2026-111160
LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...
Cooper-ndss-2022
Cooper: Testing the Binding Code of Scripting Languages with Cooperative Mutation Cooper utilize cooperative mutation to test the binding code of scripting languages to find memory-safe issues. Cooperative mutation simultaneously modifies the script code and the related document objects to explor...
Astra Linux – Vulnerability in Firefox
While the text displayed in Autofill tooltips cannot be directly read by JavaScript, it was rendered using page fonts. Side-channel attacks on the text using specially crafted fonts could have led to this text being interpreted by the webpage. This vulnerability affects Firefox versions earlier...
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...
CVE-2026-111160: Deserialization of Untrusted Data
LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pdkvtransparams field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in...
