Search papers, labs, and topics across Lattice.
4
0
6
2
SafeFlow reveals that multi-agent systems can obscure malicious intent through task decomposition, but a semantic information-flow approach can effectively counteract this vulnerability.
MIND redefines adversarial prompt generation, achieving a staggering 95.62% success rate by intelligently interpreting model defenses rather than relying on brute-force tactics.
Contextual state poisoning can be thwarted with a robust protocol that not only secures agent memory but also allows for traceable recovery from malicious alterations.
LVLMs can be jailbroken by "Reasoning-Oriented Programming," which chains together harmless visual inputs to trigger harmful reasoning, much like return-oriented programming in traditional security exploits.
