Search papers, labs, and topics across Lattice.
Zhejiang University, Ningbo Key Laboratory of Quantum Software and Security
3
0
3
Minos achieves a remarkable average recall of 0.92 in tracking cyber attacks, showcasing the power of LLM-driven reasoning in forensic analysis.
Self-evolving LLMs can amplify adversarial threats, making every known attack lineage-persistent and exposing critical vulnerabilities that static defenses can't address.
Input guardrails are no match for multi-agent attacks: \SysName reconstructs cross-agent semantic flows to detect complex attacks that bypass traditional defenses.
