Targeted prompting and system interventions enable local LLMs such as Llama 3.1 70B to exploit 83% of tested Linux privilege escalation vulnerabilities.
In: Proceedings of the 34th Interna- tional Conference on Neural Information Processing Systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.
citing papers explorer
-
Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
Targeted prompting and system interventions enable local LLMs such as Llama 3.1 70B to exploit 83% of tested Linux privilege escalation vulnerabilities.
-
Less LLM, More Documents: Searching for Improved RAG
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.