3 papers
cs.CR2026
MetaPermit: Scalable and Auditable Access Control for AI Agents via LLM-Inferred Meta-Attributes
Hanzhang Ma, Ali Hariri, Tianxiang Shen +9
The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Pro…
cs.SE2026
EnerInfer: Energy-Aware On-Device LLM Inference
Bohua Zou, Nian Liu, Binqi Sun +6
On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck. E…
cs.SE2026
ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler
Bohua Zou, Debayan Roy, Dhimankumar Yogesh Airao +4
As large language models (LLMs) move from research to production, understanding how inference engines behave in real time has become both essential and elusive. Unlike general-purp…