AIConfPaper
← Search

Eleni Triantafillou

15 accepted papers

2026

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment

Yavuz Faruk Bakman, Duygu Nur Yaldiz, Eleni Triantafillou, Peter Kairouz, Salman Avestimehr, Sai Praneeth Reddy Karimireddy
ICML 2026poster

Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed ``aligned'' can exhibit misaligned behavior after fine-tuning, such as forgetting jailbreak safety features or re-surfacing knowledge tha…

Cited by 0Source ↗Scholar ↗
2026

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

Stefan Schoepf, Michael Curtis Mozer, Nicole Elyse Mitchell, Alexandra Brintrup, Georgios Kaissis, Peter Kairouz +1
ICLR 2026poster

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. T…

Cited by 0Source ↗Scholar ↗
2026

Step-resolved data attribution for looped transformers

Georgios Kaissis, David Mildenberger, Felipe Gomez, Martin Menten, Eleni Triantafillou
ICML 2026poster

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $\tau$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all…

Cited by 0Source ↗Scholar ↗
2026

You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models

Kairan Zhao, Eleni Triantafillou, Peter Triantafillou
ICML 2026poster

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 infringement. We introduce Guidance Using Attractive-Repulsive Dynamics (GUARD), a novel framework for memorization mitigation …

Cited by 0Source ↗Scholar ↗
2025

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou
NeurIPS 2025poster

Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting for example-level unlearning in vision classifiers. We make th…

Cited by 0Source ↗Scholar ↗
2025

Leveraging Per-Instance Privacy for Machine Unlearning

Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou +2
ICML 2025poster

We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al., 2024), obtaining a better utility–unlearning trade-off by replacing worst-case privacy loss bounds wi…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Kevin Klyman, Matthew Jagielski, Katja Filippova +31
NeurIPS 2025oral

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific infor…

Cited by 0Source ↗Scholar ↗
2025

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy +1
ICLR 2025poster

When deploying machine learning models in the real world, we often face the challenge of “unlearning” specific data points or subsets after training. Inspired by Domain-Adversarial Training of Neural Networks (DANN), we propose a novel algorithm,SURE, for targeted unlearning.SURE treats the proces…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

What makes unlearning hard and what to do about it

Kairan Zhao, Meghdad Kurmanji, George-Octavian Bărbulescu, Eleni Triantafillou, Peter Triantafillou
NeurIPS 2024poster

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 with users' requests to delete their data, or remove mislabeled, poisoned or otherwise problematic data. With unlearning…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2023

In Search for a Generalizable Method for Source Free Domain Adaptation

Malik Boudiaf, tom denton, Bart van Merrienboer, Vincent Dumoulin, Eleni Triantafillou
ICML 2023poster

Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data. In this work, we apply existing SFDA techniques to a challenging set of naturally-occurring distribution shifts in bioacoustics, which are very different f…

Cited by 19Source ↗PDF ↗Scholar ↗
2023

Towards Unbounded Machine Unlearning

Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes, Eleni Triantafillou
NeurIPS 2023poster

Deep machine unlearning is the problem of 'removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion (RC) (caused by mislabelled data in trained models), as well as…

Cited by 201Source ↗PDF ↗code ↗Scholar ↗
2021

Learning a Universal Template for Few-shot Dataset Generalization

Eleni Triantafillou, Hugo Larochelle, Richard Zemel, Vincent Dumoulin
ICML 2021spotlight

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To th…

Cited by 115Source ↗PDF ↗code ↗Scholar ↗
2020

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu +5
ICLR 2020poster

Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To address this limitation, we propose Meta-Dataset: a new bench…

Cited by 788Source ↗code ↗Scholar ↗
2018

Meta-Learning for Semi-Supervised Few-Shot Classification

Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum +2
ICLR 2018poster

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes repr…

Cited by 1791Source ↗PDF ↗code ↗Scholar ↗