Papers by Alexandre Araujo

1 papers
Stronger Universal and Transferable Attacks by Suppressing Refusals (2025.naacl-long)

Copied to clipboard

Challenge: Efforts have focused on aligning models to human preferences (RLHF) . yet, it is believed that such optimization-based attacks are sample-specific.
Approach: They propose an algorithm to embed a "safety feature" into models to make them safe for mass deployment.
Outcome: The proposed attack achieves 25% success rate against the state-of-the-art Circuit Breaker defense, compared to 2.5% by white-box GCG.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations