Search papers, labs, and topics across Lattice.
4
0
6
Results show that, for proximity-defined manipulation hazards, margin selection and fallback strategy can matter more than predicate structure in determining the safety--utility trade-off of a runtime filter.
Forget red-teaming, POLARIS automatically turns safety policies into attack strategies, finding more LLM vulnerabilities with verifiable traceability.
The trustworthiness of LLM-enabled applications hinges not on further model improvements, but on establishing system-level threat monitoring to detect post-deployment anomalies.
Self-evolving LLM agents can be persistently compromised by injecting malicious payloads into their long-term memory, turning them into "zombie agents" that execute unauthorized actions across sessions.
