5 papers
Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models
Huzaifa Arif, Pin-Yu Chen, Alex Gittens +2
With the increasing reliance on AI models for weather forecasting, it is imperative to evaluate their vulnerability to adversarial perturbations. This work introduces Weather Adapt…
Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models
Huzaifa Arif, Keerthiram Murugesan, Ching-Yun Ko +3
We propose patching for large language models (LLMs) like software versions, a lightweight and modular approach for addressing safety vulnerabilities. While vendors release improve…
PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
Huzaifa Arif, Keerthiram Murugesan, Payel Das +2
This paper explores inference-time data leakage risks of deep neural networks (NNs), where a curious and honest model service provider is interested in retrieving users' private da…
Aligners: Decoupling LLMs and Alignment
Lilian Ngweta, Mayank Agarwal, Subha Maity +3
Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be r…
piCholesky: Polynomial Interpolation of Multiple Cholesky Factors for Efficient Approximate Cross-Validation
Da Kuang, Alex Gittens, Raffay Hamid
The dominant cost in solving least-square problems using Newton's method is often that of factorizing the Hessian matrix over multiple values of the regularization parameter ().…