Adversarial Robustness

Follow this topic Ask about this topic

Adversarial robustness asks whether a model still predicts or acts reliably when an attacker makes small, strategic changes to its inputs, training data, or operating environment. Common approaches include adversarial training, which exposes models to attacks during learning; randomized smoothing and other certification methods, which provide conditional guarantees; and input purification, representation regularization, and test-time adaptation. Evaluations span image classifiers and detectors, language and multimodal models, graphs, time series, and safety-critical systems, using both empirical attacks and formal bounds. A central tension is that gains can depend on the attack, data, and deployment setting, while stronger robustness may cost clean accuracy or compute; adaptive, realistic evaluation and guarantees that match real threats remain open challenges.

Latest papers

481 papers49 papers in the last four weeks, up 26% on the four weeks before. 0.3% of all new papers.

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
SORA: Free Second-Order Attacks in Fast Adversarial Training
May 30, 2026Mazdak Teymourian, Ramtin Moslemi, Farzan Rahmani +1Adversarial Training Neural Network Generalization
Department of Computer Engineering, Sharif University of Technology, Tehran, Iran.
Easy, robust approximate message passing for planted spike models
May 30, 2026Misha Ivkov, Tselil SchrammRandom Matrix Theory Principal Component Analysis
*Stanford University. · †Stanford University.
Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detection
May 29, 2026Jung Heum Woo, Eun-Kyu LeeAdversarial Patch Attacks Adversarial Robustness
School of Information Technology Incheon National University Incheon 22012, Republic of Korea
TASER: Task-Aware Stein Regularisation for Geometry-Driven Smoothness
May 28, 2026Michał Kozyra, Gesine ReinertDistribution Shift Robustness Neural Network Robustness
Department of Statistics, University of Oxford, United Kingdom
AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness
May 28, 2026Xiaoyong, Yuan, Lan +1Adversarial Patch Attacks Adversarial Robustness
Brian · Clemson University · Clemson, SC, USA +1
A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers
May 28, 2026Hannah Gao, Isha Agarwal, Dylan Hadfield-Menell +1Adversarial Training Fine-Tuning
Massachusetts Institute of Technology · MIT Cambridge, MA
Improving Adversarial Robustness of Attribution via Implicit Regularization
May 28, 2026Amir Mehrpanah, Matteo Gamba, Hossein AzizpourTransformer Interpretability Neural Network Robustness
Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Computer Science, Brown University, USA · Science for Life Laboratory, Stockholm, Sweden
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
May 28, 2026Santanu Das, Sagnik Chatterjee, Jatin BatraSingle-Index Models Adversarial Robustness
School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai, India.
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
Quantum-Enhanced Adversarial Robustness in Artificial Intelligence
May 27, 2026Jaydip SenAdversarial Robustness Quantum Machine Learning
Praxis Business School, India
Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification
May 27, 2026Yaoyang Luo, Zhi Zheng, Ziwei Zhao +5Multi-Agent LLM Systems Fake News Detection
University of Science and Technology of China · North Automatic Control Technology Institute · Shenzhen Institute for Advanced Study, UESTC
Density-aware Sample-specific Attack
May 27, 2026Qiyuan Wang, Yao Li, Raymond K. W. WongBackdoor Attacks Adversarial Robustness
Texas A&M University · University of North Carolina at Chapel Hill
When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study
May 26, 2026Jun Yan, Weiquan Huang, Jiankai Zuo +4Adversarial Training Orthogonal Optimization
IT College, Shanghai Ocean University, Shanghai, 201306 · School of Computer Science and Technology, Tongji University, Shanghai, 201804 · SEIE, Suzhou University of Science and Technology, Suzhou, 215009 +2
Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models
May 25, 2026Xiao Liu, Jiaxiang Liu, Boci Peng +6VLM Robustness Prompt Learning
University of Macau · Guangdong Institute of Intelligence Science and Technology · Peking University +4
Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models
May 25, 2026Jianwei TaiNeural Network Robustness Adversarial Robustness
School of Internet, Anhui University
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
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
May 25, 2026Aditya SridharConcept Bottleneck Models Adversarial Attacks
Independent Researcher · Atlanta, GA, USA
Making Brain-Computer Interfaces More Secure
May 22, 2026Md Fahimul Kabir Chowdhury, Gahangir HossainBrain-Computer Interfaces Adversarial Attacks
Department of Computer Science and Engineering, University of North Texas, USA · Department of Data Science, University of North Texas, USA
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
May 22, 2026Haoyuan Wang, Xiaohao Liu, Jiajie Su +2Multimodal Robustness Adversarial Robustness
Zhejiang University · National University of Singapore · Jiangxi Normal University
Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection
May 22, 2026Ahmed Sabbah, Mohammed Kharma, Radi Jarrar +2Distribution Shift Robustness Concept Drift
aDepartment of Computer Science, Birzeit University, P.O. Box 14, Birzeit, P627, West2026 Bank, Palestine · bDepartment of Computer Science, University of Central Florida, 4328 Scorpius St., Building 116, Room 246, Orlando, 32816, FL, USAMay 22
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
May 22, 2026Phuc Duc Nguyen, Quang Duc NguyenTest-Time Adaptation Adversarial Attacks
College of Computing and Data Science Nanyang Technological University Singapore
Self-supervised Adversarial Purification for Graph Neural Networks
May 22, 2026Woohyun Lee, Hogun ParkGraph Neural Networks Adversarial Robustness
Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, South Korea.
WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents
May 22, 2026Zhixiang Guo, Siyuan Liang, Shi Fu +4Adversarial Attacks on World Models Adversarial Attacks
Nanyang Technological University · University of Szeged
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
May 21, 2026Yury Belousov, Brian Pulfer, Vitaliy Kinakh +1Vision Foundation Models Adversarial Robustness
Department of Computer Science, University of Geneva, Switzerland
RADAR: Defending RAG Dynamically against Retrieval Corruption
May 21, 2026Ziyuan Chen, Yueming Lyu, Yi Liu +4Retrieval-Augmented Generation Adversarial Attacks
School of Intelligence Science and Technology, Nanjing University, Suzhou, China · City University of Hong Kong, Hong Kong, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China
Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
May 21, 2026Hongsin Lee, Hye Won ChungAdversarial Training Neural Network Robustness
School of Electrical Engineering, KAIST, Daejeon, Korea.
CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
May 21, 2026Zhi Chen, Shehab Sarar Ahmed, Chenkai Wang +2Adversarial Training Adversarial Robustness
UIUC · UIUC & BUET
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
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
May 20, 2026Muquan Li, Yingyi Ma, Yihong Huang +5Neural Network Robustness Adversarial Robustness
The Laboratory of Intelligent Collaborative Computing of UESTC, Chengdu, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Monash University, Melbourne, Australia

May 31, 2026J/K move · Enter open · S save

CEAR: Certified Ensemble Adversarial Robustness in DNNs

Daniel Sadig, Mohammadreza Maleki, Hamed Karimi, Reza Samavi

Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada · Vector Institute, Toronto, ON, Canada

Neural Network Robustness Adversarial Robustness Deep Ensembles Certified Robustness

Open paper AskPDF arXiv

Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications. State-of-the-art empirical defense mechanisms improve the robustness of DNNs through the training phase, but still struggle against adaptive white-box attacks. On the other hand, certified defenses offer provable guarantees of robustness within a specified perturbation bound. These guarantees hold regardless of the level of perturbations, even if the attacker is given full knowledge of the model. In this paper, we propose CEAR, an ensemble-based robust method that utilizes a hybrid of empirical and certified defense mechanisms. CEAR trains each network within the ensemble using varying Gaussian noise and temperatures to obfuscate gradients and logits, making the model more resistant to stronger gradient-based attacks. We then use noisy logits and propose two different voting mechanisms to further improve robustness. Furthermore, we extend randomized smoothing to verify the robustness of ensemble-based classifiers. Our experimental evaluations on MNIST, CIFAR10, and TinyImageNet datasets demonstrate superior certified accuracy on average, increased robustness radius, and decreased transferability compared to baseline methods.