Certified Robustness

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 63

All topics

S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
Jun 11, 2026Mohammed Bouri, Mohammed Erradi, Adnane SaoudAdversarial Training Certified Robustness
College of Computing, Mohammed VI Polytechnic University, Morocco · CID Development, Morocco · ENSIAS, University Mohamed V of Rabat, Morocco
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems
Jun 10, 2026Tarun SharmaRAG Poisoning Attacks Agent Memory Poisoning
Independent Researcher
Robustness Verification of Recurrent Neural Networks with Abstraction Refinement
Jun 10, 2026Li-Jen Lin, Chih-Duo HongNeural Network Verification Neural Network Robustness
Dept. of Management Information Systems National Chengchi University Taipei, Taiwan
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
Jun 8, 2026Sherwin Varghese, Matthew Wicker, Alessio LomuscioNeural Network Verification Neural Network Robustness
Imperial College London, United Kingdom
Representation Matters in Randomized Smoothing for Audio Classification
Jun 2, 2026Jong-Ik Park, Shreyas Chaudhari, José M. F. Moura +1Randomized Smoothing Keyword Spotting
Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
RRISE: Robust Radius Inference via a Surrogate Estimator
Jun 1, 2026Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong +1Randomized Smoothing Neural Network Robustness
Carnegie Mellon University
Rethinking Evaluation Paradigms in IBP-based Certified Training
Jun 1, 2026Konstantin Kaulen, Hadar Shavit, Holger H. HoosNeural Network Verification Neural Network Robustness
Chair of AI Methodology, RWTH Aachen University, Aachen, Germany · LIACS, Leiden University, Leiden, The Netherlands
CEAR: Certified Ensemble Adversarial Robustness in DNNs
May 31, 2026Daniel Sadig, Mohammadreza Maleki, Hamed Karimi +1Neural Network Robustness Adversarial Robustness
Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada · Vector Institute, Toronto, ON, Canada
Harnessing non-adversarial robustness in large language models
May 28, 2026Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin +6LLM Fine-Tuning Neural Network Robustness
International Joint Laboratory of AI for Industry, QUST, Qingdao, China · King’s College London, London, UK · Applied AI Institute, Moscow, Russia +2
Beyond Lipschitz: Data-Driven Robustness via Discrete Modulus of Continuity
May 27, 2026Jürgen Dölz, Michael Multerer, Michele PalmaNeural Network Robustness Adversarial Robustness
Institute for Numerical Simulation University of Bonn Germany · Dalle Molle Institute for Artificial Intelligence USI Lugano Switzerland
Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
May 25, 2026Konstantinos Emmanouilidis, Tianjiao Ding, Nghia Nguyen +2Neural Network Robustness Adversarial Robustness
CS & MINDS Johns Hopkins University · CIS University of Pennsylvania
Lipschitz Optimization for Formal Verification of Homographies
May 22, 2026Jean-Guillaume Durand, Panagiotis Kouvaros, Maxime Gariel +1Neural Network Verification Certified Robustness
Joby Aviation · Safe Intelligence
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
May 20, 2026Aman Saxena, Jan Schuchardt, Yan Scholten +1Randomized Smoothing Adversarial Robustness
Department of Computer Science, Technical University of Munich · Munich Data Science Institute · MCML +1
Stress-Testing Neural Network Verifiers with Provably Robust Instances
May 16, 2026David Troxell, Yulia Alexandr, Sofia Hunt +2Neural Network Verification Neural Network Robustness
Department of Statistics & Data Science, University of California, Los Angeles · Department of Mathematics, University of California, Los Angeles · Max Planck Institute for Mathematics in the Sciences, Leipzig
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
May 14, 2026Hengjie Liu, Zhenya Zhang, Jianjun ZhaoNeural Network Verification Formal Verification
Kyushu University, Fukuoka, Japan · National Institute of Informatics, Tokyo, Japan
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
May 13, 2026Blaise Delattre, Hengyu Wu, Paul Caillon +2Multimodal Robustness Randomized 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
Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
May 11, 2026Taha Entesari, Mahyar FazlyabNeural Network Verification Neural Network Robustness
Johns Hopkins University
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +1Randomized Smoothing Jailbreak Robustness
Xidian University · Xi’an Jiaotong University
Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
May 8, 2026Navid Rezazadeh, Arash Gholami DavoodiSoftmax Attention Neural Network Verification
University of California, Irvine · Carnegie Mellon University
Fortifying Time Series: DTW-Certified Robust Anomaly Detection
May 8, 2026Shijie Liu, Tansu Alpcan, Christopher Leckie +1Adversarial Robustness Certified Robustness
Department of Electrical and Electronic Engineering University of Melbourne, Melbourne, Australia · School of Computing and Information Systems University of Melbourne, Melbourne, Australia
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption
May 8, 2026Xue Tan, Yi Zheng, Chang Huo +7Retrieval-Augmented Generation RAG Poisoning Attacks
School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China · Department of Computer Science, Worcester Polytechnic Institute, MA, USA
Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity
May 2, 2026Joy Dhar, Song Xia, Manish Kumar Pandey +5Randomized Smoothing Neural Network Robustness
1Indian Institute of Technology Ropar · 2Nanyang Technological University · 3RoentGen Health +5
Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks
May 1, 2026Emma Andrews, Nahyeon Kim, Prabhat MishraAdversarial Training Adversarial Robustness
University of Florida, Gainesville, FL, USA
Laplace-Bridged Randomized Smoothing for Fast Certified Robustness
Apr 27, 2026Miao Lin, MD Saifur Rahman Mazumder, Feng Yu +2Randomized Smoothing Neural 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
Certified geometric robustness -- Super-DeepG
Apr 27, 2026Noémie Cohen, Mélanie Ducoffe, Christophe Gabreau +2Neural Network Verification Neural Network Robustness
Airbus CR\&T · Airbus · French Aerospace Lab, ONERA
GeoCert: Certified Geometric AI for Reliable Forecasting
Apr 25, 2026Regina Zhang, Zongru Li, Honggang Wen +4Neural Network Verification Time Series Forecasting
Department of Biomedical Informatics & Data Science, Yale University, US · School of Computing and Data Science, Nanyang Technological University, Singapore. · Department of Computer Science, The University of Hong Kong, Hong Kong SAR +1
Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
Apr 22, 2026Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo +2Randomized Smoothing Adversarial 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
The Cost of Relaxation: Evaluating the Error in Convex Neural Network Verification
Apr 20, 2026Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1Neural Network Verification Certified Robustness
Foundation for Research and Technology – Hellas, Heraklion, Greece · University of Crete, Heraklion, Greece · Catalan Institution for Research and Advanced Studies, Barcelona, Spain +1
Lipschitz-Based Robustness Certification Under Floating-Point Execution
Mar 6, 2026Toby MurrayNeural Network Verification Neural Network Robustness
University of Melbourne, Australia
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
Dec 1, 2025Zixia Wang, Gaojie Jin, Jia Hu +1Randomized Smoothing Adversarial Robustness of Language Models
University of Exeter

Jun 11, 2026, cs.CLJ/K move · Enter open · S save

S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP

Mohammed Bouri, Mohammed Erradi, Adnane Saoud

College of Computing, Mohammed VI Polytechnic University, Morocco · CID Development, Morocco · ENSIAS, University Mohamed V of Rabat, Morocco

Adversarial Training Certified Robustness Adversarial Text Attacks

Open paper AskPDF arXiv

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.

Momentum

Related topics

Latest papers 63