Search papers, labs, and topics across Lattice.
4
0
7
30
Contextual information can dramatically amplify the success of semantic-shift jailbreaks, with a new framework achieving a 74.6% attack success rate.
C2Btor outperforms traditional verification tools by leveraging hardware model checking, solving 101 more tasks than CBMC in a rigorous benchmark evaluation.
LLMs' impressive code generation skills crumble when faced with the messy reality of ambiguous requirements, highlighting a critical gap in their ability to handle real-world software development scenarios.
LLM agents controlling real-world tools are alarmingly easy to manipulate, with an 85% success rate for privilege escalation attacks, despite exhibiting basic security awareness.
