Search papers, labs, and topics across Lattice.
3
0
3
One in ten responses from leading LLMs on privacy and security advice could be dangerously misleading, highlighting a critical gap in their reliability.
LLMs reveal surprising strengths and weaknesses in analyzing security logs, with performance heavily influenced by model design choices.
Most social media platforms govern AI-generated content by simply applying existing content moderation policies, leaving key issues like ownership and monetization largely unaddressed.
