5 papers · 1 filter
Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
Jiahao Zhang, Lujing Zhang, Keltin Grimes +3
A recurring challenge in preference fine-tuning (PFT) is handling (i.e., cyclic) preferences. Intransitive preferences often stem from either …
From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming
Anusha Sinha, Keltin Grimes, James Lucassen +4
A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI,…
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
Keltin Grimes, Marco Christiani, David Shriver +1
Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These method…
Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning
Keltin Grimes, Collin Abidi, Cole Frank +1
Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in inter…
The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability
Stephen Casper, Jieun Yun, Joonhyuk Baek +13
Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying…