A generative adversarial attack targeting low-level neurons for boosting adversarial transferability
Krishna Kanth
KKNakka
AI & ML interests
None yet
Recent Activity
authored
a paper
4 days ago
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
authored
a paper
4 days ago
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
updated
a model
10 days ago
KKNakka/NAT
Organizations
None yet
