SOURCE-LINKED INTELLIGENCE

Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, the inference engine is an attractive target for a misaligned model. For example, if a model can trigger exploits in that engine merely by generating specially-crafted output tokens,

Read original source ↗ Open in workspace

recordType

paper

region

Global