English
Related papers

Related papers: Infusion: Shaping Model Behavior by Editing Traini…

200 papers

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC and TRAK,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Wenjie Li , Jiawei Li , Pengcheng Zeng , Christian Schroeder de Witt , Ameya Prabhu , Amartya Sanyal

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in…

Machine Learning · Computer Science 2025-05-27 Bruno Mlodozeniec , Runa Eschenhagen , Juhan Bae , Alexander Immer , David Krueger , Richard Turner

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate…

Machine Learning · Computer Science 2024-10-08 Chhavi Yadav , Ruihan Wu , Kamalika Chaudhuri

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

Machine Learning · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…

Machine Learning · Computer Science 2021-04-28 Sanjay Seetharaman , Shubham Malaviya , Rosni KV , Manish Shukla , Sachin Lodha

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Cryptography and Security · Computer Science 2023-12-15 Lukas Struppek , Martin B. Hentschel , Clifton Poth , Dominik Hintersdorf , Kristian Kersting

Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate…

Machine Learning · Computer Science 2025-10-31 Ishika Agarwal , Dilek Hakkani-Tür

Diffusion models have become increasingly popular for synthesizing high-quality samples based on training datasets. However, given the oftentimes enormous sizes of the training datasets, it is difficult to assess how training data impact…

Machine Learning · Statistics 2023-06-06 Zheng Dai , David K Gifford

Influence functions approximate the effect of training samples in test-time predictions and have a wide variety of applications in machine learning interpretability and uncertainty estimation. A commonly-used (first-order) influence…

Machine Learning · Computer Science 2021-02-12 Samyadeep Basu , Philip Pope , Soheil Feizi

Recently, influence functions present an apparatus for achieving explainability for deep neural models by quantifying the perturbation of individual train instances that might impact a test prediction. Our objectives in this paper are…

Computation and Language · Computer Science 2024-03-12 Somnath Banerjee , Maulindu Sarkar , Punyajoy Saha , Binny Mathew , Animesh Mukherjee

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human preference datasets, are often noisy. The relatively small size…

Machine Learning · Computer Science 2025-07-22 Daniel Fein , Gabriela Aranguiz-Dias

Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…

Machine Learning · Computer Science 2020-06-30 Abigail Goldsteen , Gilad Ezov , Ariel Farkash

Training data attribution (TDA) methods offer to trace a model's prediction on any given example back to specific influential training examples. Existing approaches do so by assigning a scalar influence score to each training example, under…

Machine Learning · Computer Science 2023-03-15 Kelvin Guu , Albert Webson , Ellie Pavlick , Lucas Dixon , Ian Tenney , Tolga Bolukbasi

Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly understood. Influence analysis partially demystifies training's…

Machine Learning · Computer Science 2024-04-02 Zayd Hammoudeh , Daniel Lowd

A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimating this influence enables critical applications, including…

Machine Learning · Computer Science 2025-10-15 Narine Kokhlikyan , Kamalika Chaudhuri , Saeed Mahloujifar

Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and…

Machine Learning · Computer Science 2024-07-30 Tong Xie , Haoyu Li , Andrew Bai , Cho-Jui Hsieh

Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer…

Machine Learning · Computer Science 2023-03-22 Yulong Tian , Fnu Suya , Anshuman Suri , Fengyuan Xu , David Evans

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Machine Learning · Computer Science 2021-01-28 Melissa Chase , Esha Ghosh , Saeed Mahloujifar
‹ Prev 1 2 3 10 Next ›