English
Related papers

Related papers: On the Robustness Tradeoff in Fine-Tuning

200 papers

While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This…

Machine Learning · Computer Science 2024-07-23 Yatong Bai , Brendon G. Anderson , Aerin Kim , Somayeh Sojoudi

Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Pascal Zimmer , Sébastien Andreina , Giorgia Azzurra Marson , Ghassan Karame

While $\mathcal{H}_\infty$ methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastically reduced. Though this fundamental tradeoff between…

Systems and Control · Electrical Eng. & Systems 2023-05-29 Bruce D. Lee , Thomas T. C. K. Zhang , Hamed Hassani , Nikolai Matni

We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of…

Machine Learning · Statistics 2019-09-10 Dimitris Tsipras , Shibani Santurkar , Logan Engstrom , Alexander Turner , Aleksander Madry

We derive a fundamental trade-off between standard and adversarial risk in a rather general situation that formalizes the following simple intuition: "If no (nearly) optimal predictor is smooth, adversarial robustness comes at the cost of…

Machine Learning · Statistics 2025-07-01 Sohail Bahmani

Adversarially robust training has been shown to reduce the susceptibility of learned models to targeted input data perturbations. However, it has also been observed that such adversarially robust models suffer a degradation in accuracy when…

Systems and Control · Electrical Eng. & Systems 2023-02-07 Thomas T. C. K. Zhang , Bruce D. Lee , Hamed Hassani , Nikolai Matni

While $\mathcal{H}_\infty$ methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastically reduced. Though this fundamental tradeoff between…

Systems and Control · Electrical Eng. & Systems 2022-03-22 Bruce D. Lee , Thomas T. C. K. Zhang , Hamed Hassani , Nikolai Matni

There remain many open questions pertaining to the scaling behaviour of Transformer architectures. These scaling decisions and findings can be critical, as training runs often come with an associated computational cost which have both…

Computation and Language · Computer Science 2022-02-01 Yi Tay , Mostafa Dehghani , Jinfeng Rao , William Fedus , Samira Abnar , Hyung Won Chung , Sharan Narang , Dani Yogatama , Ashish Vaswani , Donald Metzler

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Hadi Salman , Andrew Ilyas , Logan Engstrom , Ashish Kapoor , Aleksander Madry

Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense…

Information Retrieval · Computer Science 2025-06-02 Yu-An Liu , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

Federated learning (FL) has emerged as a transformative paradigm for edge intelligence, enabling collaborative model training while preserving data privacy across distributed personal devices. However, the inherent volatility of edge…

Machine Learning · Computer Science 2025-11-04 Obaidullah Zaland , Feras M. Awaysheh , Sawsan Al Zubi , Abdul Rahman Safi , Monowar Bhuyan

Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes remain limited. We present a controlled comparison of six…

Computation and Language · Computer Science 2026-01-21 Daniel Vennemeyer , Punya Syon Pandey , Phan Anh Duong , Michael Umeokoli , Samuel Ratnam

This work focuses on the problem of hyper-parameter tuning (HPT) for robust (i.e., adversarially trained) models, shedding light on the new challenges and opportunities arising during the HPT process for robust models. To this end, we…

Machine Learning · Computer Science 2024-06-14 Pedro Mendes , Paolo Romano , David Garlan

To protect multicores from soft-error perturbations, resiliency schemes have been developed with high coverage but high power and performance overheads. Emerging safety-critical machine learning applications are increasingly being deployed…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-11 Qingchuan Shi , Hamza Omar , Omer Khan

Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how…

Machine Learning · Computer Science 2022-09-23 Vahid Partovi Nia , Alireza Ghaffari , Mahdi Zolnouri , Yvon Savaria

A key step in many perceptual decision tasks is the integration of sensory inputs over time, but fundamental questions remain about how this is accomplished in neural circuits. One possibility is to balance decay modes of membranes and…

Neurons and Cognition · Quantitative Biology 2011-11-29 Nicholas Cain , Andrea K. Barreiro , Michael Shadlen , Eric Shea-Brown

In this paper we prove the existence of a fundamental trade-off between accuracy and robustness in perception-based control, where control decisions rely solely on data-driven, and often incompletely trained, perception maps. In particular,…

Optimization and Control · Mathematics 2020-03-18 Abed AlRahman Al Makdah , Vaibhav Katewa , Fabio Pasqualetti

Current methods for training robust networks lead to a drop in test accuracy, which has led prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning. We take a closer look at this phenomenon and first show…

Machine Learning · Computer Science 2020-07-14 Yao-Yuan Yang , Cyrus Rashtchian , Hongyang Zhang , Ruslan Salakhutdinov , Kamalika Chaudhuri

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. We…

Computer Vision and Pattern Recognition · Computer Science 2021-11-10 Sylvestre-Alvise Rebuffi , Sven Gowal , Dan A. Calian , Florian Stimberg , Olivia Wiles , Timothy Mann

We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning…

Machine Learning · Computer Science 2019-06-25 Hongyang Zhang , Yaodong Yu , Jiantao Jiao , Eric P. Xing , Laurent El Ghaoui , Michael I. Jordan