From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning? Paper • 2602.10771 • Published 7 days ago
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage Paper • 2507.02332 • Published Jul 3, 2025 • 1
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability Paper • 2508.16937 • Published Aug 23, 2025
NAT Collection A generative adversarial attack targeting low-level neurons for boosting adversarial transferability • 2 items • Updated 26 days ago
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders Paper • 2507.15227 • Published Jul 21, 2025