Tagged "model-security"
8 articles tagged model-security, 9 April 2026 to 7 August 2026. Newest first.
-
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems
New research paper presents attack techniques against sparsity-optimized LLM serving systems, highlighting security and robustness considerations for local inference deployments.
-
Vivo Unveils Security Solution for On-Device AI at AI for Good Global Summit 2026
Vivo announces a comprehensive security framework designed specifically for on-device AI inference, addressing privacy and security concerns in edge deployment scenarios. The solution establishes best practices for protecting user data during local model execution.
-
llama.cpp GGUF Parser Flaws: Critical Integer Overflow Enables Arbitrary Reads in Every Local AI Stack
A critical security vulnerability discovered in llama.cpp's GGUF parser threatens the integrity of local LLM deployments. The flaw allows attackers to read arbitrary memory through malicious model files.
-
Claude Opus 4.7 System Prompt Leaks Raise Local Deployment Questions
Security researchers report Claude Opus 4.7 randomly leaking its system prompt, highlighting vulnerabilities in proprietary models and reinforcing the case for transparent, locally-controlled LLM deployments.
-
Show HN: Minimal Linux Sandboxes to Manage AI-Generated Code with Ease
A new open-source tool for sandboxing and safely executing AI-generated code in minimal Linux environments, enabling secure local agent deployment.
-
Critical Security Flaw: Hackers Can Exploit Ollama Model Uploads to Leak Sensitive Server Data
A newly discovered vulnerability in Ollama allows attackers to exploit model uploads to extract sensitive information from local servers. This security issue highlights the importance of proper isolation and authentication when deploying LLMs locally.
-
Malicious GGUF Models Could Trigger Remote Code Execution on SGLang Servers
Security researchers have identified a critical vulnerability where specially crafted GGUF model files can achieve remote code execution on SGLang inference servers, posing significant risks to organizations running local LLM deployments.
-
Hugging Face Moves Safetensors Under PyTorch Foundation
Safetensors, the secure model serialization format, is now officially hosted by the PyTorch Foundation alongside PyTorch, vLLM, and DeepSpeed. This strengthens governance and adoption for the local LLM ecosystem.