Search papers, labs, and topics across Lattice.
2
0
2
0
Security benchmarks for LLM agents are fundamentally flawed: changing a tool's name can drastically alter reported attack success rates, invalidating cross-model comparisons.
Traditional cyber deception is breaking down: LLM-driven attack agents can now spot honeypots mid-reconnaissance and dynamically reroute their compute budgets toward real, high-value targets.
