Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
3
Adversarial manipulations can selectively sabotage the learning process of CL networks, leading to catastrophic learning that undermines both new and retained knowledge.
Adversarially-trained models may sacrifice up to 29.5 percentage points in clean accuracy compared to their vanilla counterparts, challenging the notion that robustness comes without significant cost.
