Search papers, labs, and topics across Lattice.
The Pennsylvania State University
4
0
7
Fingerprint spoofing allows adversarial providers to masquerade weak models as premium LLMs, undermining user trust in model verification processes.
Mid-tier LLMs outperform their stronger counterparts in harness self-evolution, challenging assumptions about model capability and adaptability.
Forget specific data from your LLM without retraining: ICCU learns human-readable "refusal rules" that block unwanted knowledge at inference time.
Legally mandated data deletion requests can be weaponized to stealthily cripple GNN performance, even if the model appears robust during initial training.
