5 papers
Scalable Attribution and Control of Model Behavior During Training
Sleem Abdelghafar
Attributing and controlling model behavior during training requires identifying each example's contribution quickly enough to act before the next update. However, examples in the s…
Privacy-Preserving AI Verification via Minimal Information Disclosure
Sleem Abdelghafar, Gabriel Kulp
AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive details about the model, workloa…
Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness
Sleem Abdelghafar, Maryam Aliakbarpour, Chris Jermaine +1
Auditing information disclosure across every datapoint during the training of LLMs is challenging. We propose a principled, attack-agnostic approach that uses mutual information to…
EinDecomp: Decomposition of Declaratively-Specified Machine Learning and Numerical Computations for Parallel Execution
Daniel Bourgeois, Zhimin Ding, Dimitrije Jankov +6
We consider the problem of automatically decomposing operations over tensors or arrays so that they can be executed in parallel on multiple devices. We address two, closely-linked…
TURNIP: A "Nondeterministic" GPU Runtime with CPU RAM Offload
Zhimin Ding, Jiawen Yao, Brianna Barrow +7
An obvious way to alleviate memory difficulties in GPU-based AI computing is via CPU offload, where data are moved between GPU and CPU RAM, so inexpensive CPU RAM is used to increa…