Safeguard
Tag

ml-supply-chain

Safeguard articles tagged "ml-supply-chain" — guides, analysis, and best practices for software supply chain and application security.

20 articles

AI Security

Understanding model poisoning and backdoored model weights

A poisoned model looks like any other checkpoint file. Here's how model poisoning attacks work, real incidents on Hugging Face, and how detection and provenance checks catch them.

Aug 4, 20267 min read
Regulatory Compliance

Analysis of pickle file deserialization vulnerabilities i...

CVE-2025-32434 shows PyTorch's "safe" weights_only loading could still be bypassed for code execution — a pickle deserialization vulnerability with real supply-chain consequences.

Aug 4, 20268 min read
AI Security

Understanding membership inference attacks against traine...

Membership inference attacks let adversaries confirm if your data trained a model, exposing privacy leakage in ML models and training data inference risks.

Jul 30, 20267 min read
Open Source Security

The torchtriton Dependency Confusion Attack on PyTorch-Ni...

How a namespace gap on PyPI let a malicious "torchtriton" package hijack PyTorch-nightly installs for five days, and what it teaches about ML supply chain security.

Jul 29, 20267 min read
AI Security

vLLM CVE-2025-62164: Tensor Deserialization RCE

vLLM 0.10.2-0.11.0 deserialized user-supplied PyTorch tensors via torch.load() in the Completions API. Memory corruption, potential RCE.

Jul 26, 20265 min read
AI Security

vLLM CVE-2025-66448: Auto-Map RCE via Model Configs

A critical RCE in vLLM allows malicious model configs to bypass trust_remote_code=False. We analyze the bug, the patch, and what every vLLM operator should do.

Jul 24, 20267 min read
AI Security

ShadowMQ: 30+ RCE Flaws Across AI Inference Engines

Oligo Security disclosed ShadowMQ in November 2025: ZeroMQ-and-pickle deserialization patterns copy-pasted across vLLM, Meta Llama, TensorRT-LLM, and others. We dissect the pattern.

Jul 22, 20267 min read
AI Security

Training Data Provenance for Enterprise Fine-Tuning

Fine-tuning corpora are supply chain artifacts. We cover the provenance signals, attestations, and drift controls enterprises need before pushing weights to prod.

Jul 22, 20265 min read
AI Security

Embedding Model Supply Chain Risks

Embedding models are the silent dependency under every RAG system. We cover poisoning, deprecation, and provenance gaps that break retrieval in production.

Jul 3, 20265 min read
AI Security

Hugging Face as Malware CDN and Exfiltration Backend: The DPRK-Linked npm Campaign of May 2026

OX Security disclosed a DPRK-aligned campaign that abused Hugging Face as a malware host and data-exfiltration backend, using public repos to serve second-stage payloads and private datasets to receive stolen developer secrets.

May 22, 202611 min read
AI Security

The Fake OpenAI 'privacy-filter' Model: How a Typosquat Hit #1 on Hugging Face in May 2026

A repository named Open-OSS/privacy-filter impersonated OpenAI's release, copied its model card verbatim, and shipped a loader.py that pulled an infostealer. It reached #1 trending with ~244,000 downloads before removal.

May 12, 202610 min read
AI Security

PyTorch CVE-2025-32434: weights_only=True No Longer Safe

A critical PyTorch RCE bypassed the safety property of torch.load(weights_only=True). We analyze the bug and explain why safetensors should now be the default.

Apr 29, 20267 min read

Self-healing security runs on Safeguard.

Your first fix PR is minutes away.

No sales call required, even your agent can complete the purchase over MCP.

ml-supply-chain — Safeguard Blog