attack-attention

Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks Official PyTorch implementation of the paper "Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks" , accepted in the Adversarial Machine Learning on Computer Vision: Foundation Models + X ADV...

Noctyra

Noctyra Noctyra is an AST-based framework designed for code transformation and deobfuscation. It provides a modular pipeline to analyze and simplify Python source code by resolving complex expressions and logic. Overview The project aims to provide a flexible environment for processing Python's...

llama-factory-webui-rce-cve-2026-58116-trust-remote-code-model-path-injection

CVE-2026-58116 — LLaMA-Factory WebUI RCE via trustremotecode Proof of concept for CVE-2026-58116 CVSS 9.8 Critical: remote code execution in LLaMA-Factory = v0.9.5. The LLaMA-Factory WebUI hardcodes trustremotecode=True when loading a model src/llamafactory/webui/chatter.py:139 and...

CVE-2024-11393

CVE-2024-11393 Hugging Face Transformers MaskFormer Model Deserialization of Untrusted Data Remote Code Execution Vulnerability High-level overview and effects of the vulnerability: The vulnerability allows an attacker to execute arbitrary code on the host machine by supplying a malicious...

CVE-2024-11392

CVE-2024-11392 Hugging Face Transformers MobileViTV2 Deserialization of Untrusted Data Remote Code Execution Vulnerability High-level overview and effects of the vulnerability: The vulnerability allows an attacker to execute arbitrary code on the host machine by supplying a malicious configuratio...

Pickle-Deserialization-Exploit-in-Transformers

Exploiting Pickle Deserialization Vulnerability in Transformers Experiment Introduction Introduces the pickle deserialization mechanism and its reduce attack principle, reproduces the deserialization vulnerability CVE-2024-3568 in the Hugging Face Transformers library, analyzes security risks in...

CVE-2026-80047

A flaw was found in the Hugging Face Transformers library. A remote attacker could exploit this vulnerability by enticing a user to load a model using the GenerativePreTrainedModel.loadcustomgenerate function. This function writes remote Python files to the local disk without requiring explicit...

CVE-2024-11394

CVE-2024-11394 Hugging Face Transformers Trax Model Deserialization of Untrusted Data Remote Code Execution Vulnerability High-level overview and effects of the vulnerability: The vulnerability allows an attacker to execute arbitrary code on the host machine by supplying a malicious reformer trax...

CVE-2026-23001-Hugging-Face-Transformers-Model-Deserialization-Arbitrary-Code-via-Pickle-

CVE-2026-23001 – Hugging Face Transformers Model Deserialization RCE Overview Hugging Face models saved with torch.save use Python’s pickle serialization, which is inherently unsafe. If a user downloads a seemingly legitimate model from a repository, loading it can trigger arbitrary code executio...

CVE-2026-7669-PoC

CVE-2026-7669 SGLang silently overrides trustremotecode=False to True and re-invokes AutoTokenizer.frompretrained whenever transformers v5 returns a TokenizersBackend object. A model with a custom tokenizerclass and an automap pointing at tokenizer.py reaches arbitrary code execution inside the...

CVE-2026-22807_Range

🛡️ CVE-2026-22807 Simulation: AI Supply Chain RCE Target Range ⚠️ Disclaimer This project is intended solely for security research and educational purposes , aiming to demonstrate the supply chain attack principle Remote Code Execution during AI model loading. Do not use the generated malicious...

Hugging Face Transformers downloads custom generation code before trust consent

A vulnerability in Hugging Face Transformers versions 4.49.0, = 5.8.1 allows remote Python files to be written to local disk without user consent when using GenerativePreTrainedModel.loadcustomgenerate. The function fetches and caches a remote module file before performing the required...

sentence-transformers local model loading bypasses trust_remote_code and executes custom Python

sentence-transformers contains a security control bypass vulnerability that allows attackers to achieve arbitrary code execution by exploiting a logic flaw in the importmoduleclass helper within sentencetransformers/util/misc.py, where the guard condition includes an 'or...

CLSA-2026-1790851862 TuxCare security update for sentence-transformers (1 CVE)

TuxCare rebuilt sentence-transformers to address 1 CVE. Fixed in 2.7.0.post3+tuxcare...

CLSA-2026-1790831175 TuxCare security update for transformers (1 CVE)

TuxCare rebuilt transformers to address 1 CVE. Fixed in 4.57.6.post5+tuxcare...

Security Bulletin: Multiple vulnerabilities in IBM MQ Agent images

Summary Multiple vulnerabilities were addressed in IBM MQ Agent images Vulnerability Details CVEID:CVE-2026-75104 DESCRIPTION: Hugging Face Transformers fails to validate shard filenames in checkpoint index files, allowing attackers to read arbitrary files outside the model directory. Attackers c...

Security Bulletin: Multiple Vulnerabilities in IBM watsonx Code Assistant On Prem

Summary Multiple vulnerabilities were addressed in IBM watsonx Code Assistant On Prem V5.3.1 Patch 12 Vulnerability Details CVEID:CVE-2026-12143 DESCRIPTION: form-data is a library for creating readable multipart/form-data streams. In versions through 4.0.5, the field argument to FormDataappend a...

ROOT-APP-PYPI-CVE-2026-9856 CVE-2026-9856 in transformers - Patched by Root

Root has patched CVE-2026-9856 in the transformers package for Root:PyPI. Multiple fixed versions available...

PYSEC-2026-3929 Transformers save_pretrained path traversal allows arbitrary file writes through chat template names

A vulnerability in huggingface/transformers versions 5.10.0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in the savepretrained methods of PreTrainedTokenizerBase and ProcessorMixin, where keys from the chattemplate dictionary are used directly as...

Transformers save_pretrained path traversal allows arbitrary file writes through chat template names

A vulnerability in huggingface/transformers versions 5.10.0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in the savepretrained methods of PreTrainedTokenizerBase and ProcessorMixin, where keys from the chattemplate dictionary are used directly as...