Search papers, labs, and topics across Lattice.
3
0
5
6
Learning high-level strategies can boost vulnerability reproduction success rates by over 20%, revolutionizing how we approach software security tasks.
A cleverly shaped and rendered adversarial patch can reliably spoof palmprint recognition, even across different models and datasets.
Current image generation unlearning methods are surprisingly brittle: adversarial image prompts, optimized with attention-guided masking, can effectively resurrect supposedly "forgotten" concepts.
