English
Related papers

Related papers: On the Robustness Tradeoff in Fine-Tuning

200 papers

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Machine Learning · Computer Science 2026-04-15 Qinghua Zhao , Xueling Gong , Xinyu Chen , Zhongfeng Kang , Xinlu Li

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…

Machine Learning · Computer Science 2019-12-05 Varun Chandrasekaran , Brian Tang , Nicolas Papernot , Kassem Fawaz , Somesh Jha , Xi Wu

The study of online algorithms with machine-learned predictions has gained considerable prominence in recent years. One of the common objectives in the design and analysis of such algorithms is to attain (Pareto) optimal tradeoffs between…

Machine Learning · Computer Science 2024-08-09 Spyros Angelopoulos , Christoph Dürr , Alex Elenter , Yanni Lefki

In computing, as in many aspects of life, changes incur cost. Many optimization problems are formulated as a one-time instance starting from scratch. However, a common case that arises is when we already have a set of prior assignments, and…

Data Structures and Algorithms · Computer Science 2013-02-11 Edith Cohen , Graham Cormode , Nick Duffield , Carsten Lund

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

Neural and Evolutionary Computing · Computer Science 2018-11-26 Edward Grefenstette , Robert Stanforth , Brendan O'Donoghue , Jonathan Uesato , Grzegorz Swirszcz , Pushmeet Kohli

Multiple intriguing problems are hovering in adversarial training, including robust overfitting, robustness overestimation, and robustness-accuracy trade-off. These problems pose great challenges to both reliable evaluation and practical…

Machine Learning · Computer Science 2021-10-08 Chengyu Dong , Liyuan Liu , Jingbo Shang

The reliability of a learning model is key to the successful deployment of machine learning in various applications. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. It…

Machine Learning · Computer Science 2025-05-27 Ramin Barati , Reza Safabakhsh , Mohammad Rahmati

Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net…

Machine Learning · Computer Science 2017-06-19 Osbert Bastani , Yani Ioannou , Leonidas Lampropoulos , Dimitrios Vytiniotis , Aditya Nori , Antonio Criminisi

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Cryptography and Security · Computer Science 2026-05-26 Itay Zloczower , Eyal Lenga , Gilad Gressel , Yisroel Mirsky

Deep learning models are challenged by the distribution shift between the training data and test data. Recently, the large models pre-trained on diverse data have demonstrated unprecedented robustness to various distribution shifts.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Yao Xiao , Ziyi Tang , Pengxu Wei , Cong Liu , Liang Lin

Reinforcement learning (RL) policies deployed in real-world environments must remain reliable under adversarial perturbations. At the same time, modern deep RL agents are heavily over-parameterized, raising costs and fragility concerns.…

Machine Learning · Computer Science 2025-10-16 James Pedley , Benjamin Etheridge , Stephen J. Roberts , Francesco Quinzan

This paper presents a robust fine-tuning method designed for pre-trained 3D point cloud models, to enhance feature robustness in downstream fine-tuned models. We highlight the limitations of current fine-tuning methods and the challenges of…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Zhibo Zhang , Ximing Yang , Weizhong Zhang , Cheng Jin

Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the…

Machine Learning · Computer Science 2019-03-18 Abed AlRahman Al Makdah , Vaibhav Katewa , Fabio Pasqualetti

With the prevalence of the Pretraining-Finetuning paradigm in transfer learning, the robustness of downstream tasks has become a critical concern. In this work, we delve into adversarial robustness in transfer learning and reveal the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Andong Hua , Jindong Gu , Zhiyu Xue , Nicholas Carlini , Eric Wong , Yao Qin

Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model hosting platforms like Hugging Face (HF). Thanks to these…

Software Engineering · Computer Science 2024-08-07 Hao Qin , Mingyang Li , Junjie Wang , Qing Wang

We present a more general analysis of $H$-calibration for adversarially robust classification. By adopting a finer definition of calibration, we can cover settings beyond the restricted hypothesis sets studied in previous work. In…

Machine Learning · Computer Science 2021-05-07 Pranjal Awasthi , Anqi Mao , Mehryar Mohri , Yutao Zhong

The vulnerability of deep neural networks to adversarial samples has been a major impediment to their broad applications, despite their success in various fields. Recently, some works suggested that adversarially-trained models emphasize…

Computer Vision and Pattern Recognition · Computer Science 2023-07-31 Qingwen Bu , Dong Huang , Heming Cui

Robustness of machine learning models to various adversarial and non-adversarial corruptions continues to be of interest. In this paper, we introduce the notion of the boundary thickness of a classifier, and we describe its connection with…

Mixture of Experts (MoE) have shown remarkable success in leveraging specialized expert networks for complex machine learning tasks. However, their susceptibility to adversarial attacks presents a critical challenge for deployment in robust…

Machine Learning · Computer Science 2025-05-28 Xu Zhang , Kaidi Xu , Ziqing Hu , Ren Wang

Although many fields have witnessed the superior performance brought about by deep learning, the robustness of neural networks remains an open issue. Specifically, a small adversarial perturbation on the input may cause the model to produce…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Binxiao Huang , Chaofan Tao , Rui Lin , Ngai Wong