1 citations · 2 across the 7 of their papers we have counts for
7 papers
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
Kairan Zhao, Eleni Triantafillou, Peter Triantafillou
Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infring…
Benchmarking Unlearning for Vision Transformers
Kairan Zhao, Iurie Luca, Peter Triantafillou
Machine unlearning (MU) refers to the post-training capability to remove (the influence of) training examples that are incorrect, biased, or leak sensitive/private information. MU…
Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
Akshit Achara, Peter Triantafillou, Esther Puyol-Antón +2
Deep neural networks often exploit shortcuts. These are spurious cues which are associated with output labels in the training data but are unrelated to task semantics. When the sho…
Scalability of memorization-based machine unlearning
Kairan Zhao, Peter Triantafillou
Machine unlearning (MUL) focuses on removing the influence of specific subsets of data (such as noisy, poisoned, or privacy-sensitive data) from pretrained models. MUL methods typi…
Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa +12
We present the findings of the first NeurIPS competition on unlearning, which sought to stimulate the development of novel algorithms and initiate discussions on formal and robust…
What makes unlearning hard and what to do about it
Kairan Zhao, Meghdad Kurmanji, George-Octavian Bărbulescu +2
Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply…
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
George-Octavian Barbulescu, Peter Triantafillou
LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and r…