12 papers
When Less is Enough: Efficient Inference via Collaborative Reasoning
Yilei Chen, Sharut Gupta, Yannis Paschalidis +2
In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to so…
Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle +5
Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. The standard toolkit, generat…
Machine Unlearning Fails to Remove Data Poisoning Attacks
Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu +3
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion request…
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith M. Suriyakumar, Rohan Alur, Ayush Sekhari +2
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make increm…
The Space Complexity of Learning-Unlearning Algorithms
Yeshwanth Cherapanamjeri, Sumegha Garg, Nived Rajaraman +2
We study the memory complexity of machine unlearning algorithms that provide strong data deletion guarantees to the users. Formally, consider an algorithm for a particular learning…
UCD: Unlearning in LLMs via Contrastive Decoding
Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson
Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an…