Randomized Smoothing

Ask about this topic

Overview

Randomized smoothing studies how adding random perturbations to inputs or representations can make model predictions more stable and, in many settings, yield certified bounds on the perturbations an attacker can make. Common approaches use Gaussian noise and Monte Carlo estimates, while newer methods adapt the noise or use structured, discrete, or semantically meaningful perturbations. Work spans image classification and extends to language and multimodal models, audio, regression, and trajectory prediction. A central tension is making certificates cheaper and better matched to real attacks without letting the guarantee depend on unrealistic noise assumptions or overstate empirical robustness.

Latest papers

CardsList

25 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. A Certified Robustness Framework for Backdoor Poisoning Attacks using ff-Divergences

    Oct 26, 2026Evan Rose, Alina OpreaCertified RobustnessData Poisoning Attacks

    Northeastern University

  2. The Geometry of Randomized Smoothing on Feasible Sets

    Sep 30, 2026Syed Izhan Khilji, Alireza Furutanpey, Schahram DustdarRandomized SmoothingSelective Prediction

    Technische Universität Wien · NeverBlink · Technische Universität Wien Universitat Pompeu Fabra

  3. Bundled Contact Gradients: Stabilizing Differentiable Simulation for Deployable Dynamic Tasks

    Sep 25, 2026Dyuman Aditya, Jin Cheng, Clemens Schwarke +4Robotics SimulationDifferentiable Physics

    University of Southern California, LA, USA. · ETH Zurich, Switzerland. · NVIDIA. +1

  4. Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models

    Sep 23, 2026Kian Shamsaie, Iman ModarressiRandomized SmoothingAdversarial Attacks

    People Make Things

  5. Clustered Randomized Smoothing for Stochastic Prediction Functions

    Aug 12, 2026Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann +3Multimodal RobustnessRandomized Smoothing

    Delft Center for Systems and Control, Delft University of Technology · Cognitive Robotics, Delft University of Technology · University of Stuttgart +1

  6. Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

    Jul 15, 2026Zhenpeng LiRandomized SmoothingNetwork Intrusion Detection

  7. Higher-Order Certified Robustness for Regression

    Jul 6, 2026Jie Zhang, Natalie FrankRobust RegressionRandomized Smoothing

    University of Washington, USA

  8. TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction

    Jun 27, 2026Liang Zhang, Gaojie Jin, Yao Shi +4Randomized SmoothingPedestrian Trajectory Prediction

    Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China · Hangzhou Institute for Advanced Study, UCAS, China +1

  9. Halt Fast! Early Stopping for Certified Robustness

    Jun 26, 2026Andrew C. Cullen, Paul Montague, Benjamin I. P. RubinsteinEfficient Neural Network InferenceEarly Stopping

    University of Melbourne · DST Group, Adelaide

  10. Representation Matters in Randomized Smoothing for Audio Classification

    Jun 2, 2026Jong-Ik Park, Shreyas Chaudhari, José M. F. Moura +1Randomized SmoothingKeyword Spotting

    Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.

  11. RRISE: Robust Radius Inference via a Surrogate Estimator

    Jun 1, 2026Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong +1Randomized SmoothingNeural Network Robustness

    Carnegie Mellon University

  12. Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing

    May 28, 2026Leyi Qi, Yiming Li, Siyuan Liang +2Diffusion Model WatermarkingRandomized Smoothing

    Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Computer Science and Engineering, Texas A&M University, USA

  13. Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy

    May 20, 2026Aman Saxena, Jan Schuchardt, Yan Scholten +1Randomized SmoothingAdversarial Robustness

    Department of Computer Science, Technical University of Munich · Munich Data Science Institute · MCML +1

  14. Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification

    May 15, 2026Daniel Brignac, Fengwei Tian, Banafsheh Latibari +2Adversarial RobustnessAdversarial Attacks

    The University of Arizona Tucson, Arizona, United States

  15. Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing

    May 13, 2026Blaise Delattre, Hengyu Wu, Paul Caillon +2Multimodal RobustnessRandomized Smoothing

    Department of Computer Science, School of Computing, Institute of Science Tokyo, Tokyo, Japan · PSL University, Paris, France · College of Computing and Data Science, Nanyang Technological University, Singapore

  16. Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

    May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +1Randomized SmoothingJailbreak Robustness

    Xidian University · Xi’an Jiaotong University

  17. Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity

    May 2, 2026Joy Dhar, Song Xia, Manish Kumar Pandey +5Randomized SmoothingNeural Network Robustness

    1Indian Institute of Technology Ropar · 2Nanyang Technological University · 3RoentGen Health +5

  18. Laplace-Bridged Randomized Smoothing for Fast Certified Robustness

    Apr 27, 2026Miao Lin, MD Saifur Rahman Mazumder, Feng Yu +2Randomized SmoothingNeural Network Robustness

    Department of Computer Science, Old Dominion University, Norfolk, VA, USA · Department of Mathematical Sciences, University of Texas at El Paso, El Paso, TX, USA · School of Cybersecurity, Old Dominion University, Norfolk, VA, USA

  19. Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks

    Apr 22, 2026Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo +2Randomized SmoothingAdversarial Attacks

    Department of Computer Applications, Cochin University of Science and Technology, India · Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Adolfo Ferrata 5, 27100, Pavia, Italy

  20. Directional Embedding Smoothing for Robust Vision Language Models

    Mar 16, 2026Ye Wang, Jing Liu, Toshiaki Koike-AkinoVLM SafetyVLM Robustness

    Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA

  21. Evaluating randomized smoothing as a defense against adversarial attacks in trajectory prediction

    Mar 11, 2026Julian F. Schumann, Eduardo Figueiredo, Frederik Baymler Mathiesen +3Probabilistic Trajectory PredictionAdversarial Robustness

    Department of Cognitive Robotics, TU Delft, Delft, Netherlands · Delft Center for Systems and Control, TU Delft, Delft, Netherlands

  22. Feature-Space Smoothing: Certified Robustness of Deep Representations

    Jan 22, 2026Song Xia, Meiwen Ding, Chenqi Kong +2Adversarial RobustnessCertified Robustness

    Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Pengcheng Laboratory, Shenzhen, China

  23. CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing

    Dec 1, 2025Zixia Wang, Gaojie Jin, Jia Hu +1Randomized SmoothingSemantic Clustering

    University of Exeter

  24. Dual Randomized Smoothing: Beyond Global Noise Variance

    Dec 1, 2025Chenhao Sun, Yuhao Mao, Martin VechevRandomized SmoothingNeural Network Robustness

    Department of Computer Science, ETH Zürich, Switzerland

  25. A stochastic smoothing framework for nonconvex-nonconcave minEmax problems with applications to Wasserstein distributionally robust optimization

    Feb 24, 2025Wei Liu, Muhammad Khan, Gabriel Mancino-Ball +1Randomized SmoothingNonconvex Stochastic Optimization

    Department of Applied Mathematics, Hong Kong Polytechnic University, Hong Kong, China · Institute for Math & AI, Wuhan (IMAI), Wuhan university, China · Department of Mathematical Sciences Rensselaer Polytechnic Institute, Troy, NY, USA