English
Related papers

Related papers: Adversarial Training of Reward Models

200 papers

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Computer Vision and Pattern Recognition · Computer Science 2019-11-25 Haichao Zhang , Jianyu Wang

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Machine Learning · Computer Science 2018-01-16 Bo Luo , Yannan Liu , Lingxiao Wei , Qiang Xu

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Samarup Bhattacharya , Anubhab Bhattacharya , Abir Chakraborty

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

Machine Learning · Computer Science 2022-06-15 Kaustubh Sridhar , Souradeep Dutta , Ramneet Kaur , James Weimer , Oleg Sokolsky , Insup Lee

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…

Machine Learning · Computer Science 2021-12-24 Zhiwen Yan , Teck Khim Ng

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the…

Machine Learning · Computer Science 2020-06-11 Shufei Zhang , Kaizhu Huang , Zenglin Xu

In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance…

Machine Learning · Computer Science 2025-10-13 Soroush Mahdi , Maryam Amirmazlaghani , Saeed Saravani , Zahra Dehghanian

In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verbose but less helpful response from the LLMs can often…

Machine Learning · Computer Science 2024-02-13 Lichang Chen , Chen Zhu , Davit Soselia , Jiuhai Chen , Tianyi Zhou , Tom Goldstein , Heng Huang , Mohammad Shoeybi , Bryan Catanzaro

Large vision models have been found vulnerable to adversarial examples, emphasizing the need for enhancing their adversarial robustness. While adversarial training is an effective defense for deep convolutional models, it often faces…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Kangtao Lv , Huangsen Cao , Kainan Tu , Yihuai Xu , Zhimeng Zhang , Xin Ding , Yongwei Wang

In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…

Signal Processing · Electrical Eng. & Systems 2021-05-31 Javier Maroto , Gérôme Bovet , Pascal Frossard

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream…

Machine Learning · Computer Science 2025-03-04 Debmalya Mandal , Paulius Sasnauskas , Goran Radanovic

There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly…

Machine Learning · Computer Science 2020-01-03 Xinshi Chen , Shuang Li , Hui Li , Shaohua Jiang , Yuan Qi , Le Song

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

Machine Learning · Computer Science 2025-07-08 Buqing Nie , Yangqing Fu , Jingtian Ji , Yue Gao

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Computation and Language · Computer Science 2018-12-11 Ziming Li , Julia Kiseleva , Maarten de Rijke

Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answer and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on…

Computation and Language · Computer Science 2024-10-22 Seong-Il Park , Jay-Yoon Lee

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image…

Machine Learning · Computer Science 2026-05-19 Andreas Bergmeister , Stefanie Jegelka , Nikolas Nüsken , Carles Domingo-Enrich , Jakiw Pidstrigach

Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial…

Cryptography and Security · Computer Science 2025-11-20 Kyle Domico , Jean-Charles Noirot Ferrand , Ryan Sheatsley , Eric Pauley , Josiah Hanna , Patrick McDaniel

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Artificial Intelligence · Computer Science 2024-11-01 Debangshu Banerjee , Aditya Gopalan