English
Related papers

Related papers: GSmooth: Certified Robustness against Semantic Tra…

200 papers

This paper tackles the pressing challenge of preserving semantic meaning in communication systems constrained by limited bandwidth. We introduce a novel reinforcement learning framework that achieves per-dimension unequal error protection…

Machine Learning · Computer Science 2026-03-02 Moirangthem Tiken Singh , Adnan Arif

Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is…

Machine Learning · Computer Science 2020-10-23 Zifan Wang , Haofan Wang , Shakul Ramkumar , Matt Fredrikson , Piotr Mardziel , Anupam Datta

Randomized smoothing is currently the state-of-the-art method that provides certified robustness for deep neural networks. However, due to its excessively conservative nature, this method of incomplete verification often cannot achieve an…

Machine Learning · Computer Science 2023-12-29 Bo-Han Kung , Shang-Tse Chen

Autonomous robots require change-robust spatial-semantic reasoning: using spatial and semantic knowledge to decide where to go, how to get there, and where the robot is despite environmental change. Existing approaches typically attach…

Robotics · Computer Science 2026-05-05 Jiaming Wang , Jizhuo Chen , Diwen Liu , Atharva Ghotavadekar , Jiaxuan Da , Linh Kästner , Harold Soh

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-time defenses (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jiaming Liang , Chi-Man Pun

Despite Graph neural networks' significant performance gain over many classic techniques in various graph-related downstream tasks, their successes are restricted in shallow models due to over-smoothness and the difficulties of…

Machine Learning · Computer Science 2023-12-15 Jin Li , Qirong Zhang , Shuling Xu , Xinlong Chen , Longkun Guo , Yang-Geng Fu

In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To do so, we instantiate the denoised smoothing approach of…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Florian Tramer , Krishnamurthy Dj Dvijotham , Leslie Rice , Mingjie Sun , J. Zico Kolter

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Omid Poursaeed , Tianxing Jiang , Harry Yang , Serge Belongie , SerNam Lim

Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness guarantees on the…

Machine Learning · Computer Science 2023-07-18 Aounon Kumar , Alexander Levine , Tom Goldstein , Soheil Feizi

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

Machine Learning · Computer Science 2024-05-28 Jieren Deng , Hanbin Hong , Aaron Palmer , Xin Zhou , Jinbo Bi , Kaleel Mahmood , Yuan Hong , Derek Aguiar

In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks -- small modifications of the input that change the predictions. Besides rigorously studied $\ell_p$-bounded additive…

Machine Learning · Computer Science 2022-08-16 Mikhail Pautov , Nurislam Tursynbek , Marina Munkhoeva , Nikita Muravev , Aleksandr Petiushko , Ivan Oseledets

In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations…

Machine Learning · Computer Science 2019-10-25 Alexander Levine , Soheil Feizi

Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e.g. translations, rotations, etc. Current input deformation certification…

Machine Learning · Computer Science 2021-12-21 Motasem Alfarra , Adel Bibi , Naeemullah Khan , Philip H. S. Torr , Bernard Ghanem

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical…

Computation and Language · Computer Science 2024-12-20 Junyu Luo , Xiao Luo , Kaize Ding , Jingyang Yuan , Zhiping Xiao , Ming Zhang

Randomized smoothing (RS) is an effective and scalable technique for constructing neural network classifiers that are certifiably robust to adversarial perturbations. Most RS works focus on training a good base model that boosts the…

Machine Learning · Computer Science 2021-09-20 Chen Chen , Kezhi Kong , Peihong Yu , Juan Luque , Tom Goldstein , Furong Huang

Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…

Computation and Language · Computer Science 2025-11-17 Cristina Pinneri , Christos Louizos

Training large language models (LLMs) with reinforcement learning (RL) methods such as PPO and GRPO commonly relies on ratio clipping to stabilise updates. While effective at preventing instability, clipping discards information, introduces…

Machine Learning · Computer Science 2026-02-02 Madeleine Dwyer , Adam Sobey , Adriane Chapman

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…

Machine Learning · Computer Science 2023-04-13 Linyi Li , Tao Xie , Bo Li

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has…

Machine Learning · Computer Science 2024-06-21 Harrison Gietz , Jugal Kalita

This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve…

Computation and Language · Computer Science 2024-02-21 Chakib Fettal , Lazhar Labiod , Mohamed Nadif