Search papers, labs, and topics across Lattice.
Polytechnique Montr茅al
4
0
8
Forget scaling laws: for code classification and vulnerability detection, the *right* code-specialized PLM matters more than GNN architecture or PLM size in PLM-GNN hybrids.
LLMs can exhibit surprising ethical failures and progressive degradation under sustained adversarial pressure, even when passing standard single-round safety benchmarks.
Forget retraining: this SDN-IoT defense system uses LLMs to safely evolve reinforcement learning policies through interpretable policy updates, slashing catastrophic overloads by 80%.
Despite high static quality scores, YARA rules in the wild suffer from significant noise, low recall, and a bias towards legacy threats, exposing a "double penalty" for defenders.
