A server-side request forgery vulnerability in Ollama allows attackers on the local network to read arbitrary files and make requests to internal services via the model pull endpoint. Affects all versions prior to 0.3.8.
New research demonstrates that backdoor behaviours introduced into LLMs during fine-tuning can persist through subsequent safety alignment procedures, including RLHF and adversarial training, posing significant supply chain risks.
A practical framework for implementing prompt injection detection and containment at the API gateway layer — covering input sanitisation, context isolation, output filtering, and anomaly-based detection for production LLM deployments.
A critical deserialization vulnerability in a widely-deployed ML model serving framework allows unauthenticated remote code execution via crafted model files. Patch immediately — active exploitation observed in the wild.
Researchers demonstrate that safety-aligned multimodal LLMs can be reliably jailbroken by encoding adversarial instructions as text within images, bypassing text-layer safety filters that do not process image content through the same moderation pipeline.