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.

Adversarial Robustness of Deep State Space Models for Forecasting
Apr 3, 2026Sribalaji C. Anand, George J. PappasAdversarial Robustness State Space Models
Department of Electrical and Systems Engineering, University of Pennsylvania, United States · KTH Royal Institute of Technology, Sweden
Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy
Apr 3, 2026Yang Yue, Shenjian Zhang, Yonghong Tian +2Adversarial Robustness Neural Representation Geometry
School of Computer Science, Peking University, China
A Unified Perspective on Adversarial Membership Manipulation in Vision Models
Apr 3, 2026Ruize Gao, Kaiwen Zhou, Yongqiang Chen +1Membership Inference Attacks Adversarial Robustness
Knowin AI · The Chinese University of Hong Kong · The University of Melbourne
AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection
Apr 2, 2026Vickson FerrelNetwork Intrusion Detection Encrypted Network Traffic Analysis
Faculty of Computer Science & Information Technology Universiti Malaysia Sarawak (UNIMAS), Kota Samarahan, Malaysia · Founder & Lead Architect, Vixero Technology Enterprise, Kuching, Sarawak, Malaysia
Safety, Security, and Cognitive Risks in World Models
Apr 1, 2026Manoj ParmarAdversarial Attacks on World Models World Models
SovereignAI Security Labs, Bengaluru, India
SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
Apr 1, 2026Wenjing Wang, Wenxuan Wang, Songning LaiTraffic Accident Anticipation Adversarial Robustness
Xiamen University Malaysia · Xinjiang University · HKUST(GZ)
Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery
Apr 1, 2026Deemah H. Tashman, Soumaya CherkaouiAdversarial Attacks Network Slicing
Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, Canada
Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent
Apr 1, 2026Daye Kang, Hyeongboo BaekAdversarial Attacks on Object Detectors Adversarial Robustness
University of Seoul, Seoul, South Korea
Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
Apr 1, 2026Xinyu Sun, Wanwei Liu, Haoang Chi +7Backdoor Defense Adversarial Robustness
National University of Defense Technology, Changsha, Hunan, China · Nanjing University, Nanjing, Jiangsu, China · Zhejiang University, Hangzhou, Zhejiang, China
Diffusion-Based Feature Denoising with NNMF for Robust handwritten digit multi-class classification
Mar 31, 2026Hiba Adil Al-kharsan, Róbert RajkóDiffusion-Based Denoising Handwritten Digit Recognition
Doctoral School of Computer Science, University of Szeged, Árpád tér 2, H-6720 Szeged, Hungary · University Research and Innovation Center (EKIK), Óbuda University, Bécsi út 96/b, H-1034 Budapest, Hungary
Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition
Mar 31, 2026Rongkang Dong, Cuixin Yang, Cong Zhang +2Adversarial Robustness Facial Expression Recognition
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong · School of Control Science and Engineering, Shandong University
Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
Mar 31, 2026Yunrui Yu, Xuxiang Feng, Pengda Qin +5Adversarial Robustness Adversarial Attacks
Tsinghua University · University of Macau
Detection of Adversarial Attacks in Robotic Perception
Mar 30, 2026Ziad Sharawy, Mohammad Nakshbandi, Sorin Mihai GrigorescuAdversarial Example Detection Adversarial Robustness
Department of Mechatronics and Robotics, Faculty of Electrical Engineering and Computer Science, Transylvania University of Bras,ov, Romania
ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment
Mar 30, 2026Tran Duong Minh Dai, Triet Huynh Minh Le, M. Ali Babar +2Software Vulnerability Detection Multimodal Graph Learning
Information Security Lab, University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · School of Computer Science and Information Technology, Adelaide University, Adelaide, Australia
A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
Mar 27, 2026Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed +1Adversarial Purification Adversarial Robustness
OmnAI Lab, Computer Science Department, Sapienza University of Rome, Italy · Weizmann Institute of Science, Israel
DTP-Attack: A decision-based black-box adversarial attack on trajectory prediction
Mar 27, 2026Jiaxiang Li, Jun Yan, Daniel Watzenig +1Black-Box Adversarial Attacks Adversarial Robustness
College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China. · Graz University of Technology and the Virtual Vehicle Research, Graz 8010, Austria.
Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
Mar 27, 2026Yuhang Ma, Jie Wang, Zheng YanGraph Neural Networks Adversarial Robustness
State Key Laboratory of Integrated Services Networks, School of Cyber Engineering, Xidian University, China · Hangzhou Institute of Technology, Xidian University, China
ARTA: Adversarial-Robust Multivariate Time--Series Anomaly Detection via Sparsity-Constrained Perturbations
Mar 26, 2026Hadi Hojjati, Narges ArmanfardTime-Series Anomaly Detection Adversarial Robustness
McGill University, MILA - Quebec AI Institute, Montreal, Quebec, Canada
NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs
Mar 26, 2026Inês Valentim, Nuno Antunes, Nuno LourençoAdversarial Robustness Convolutional Neural Networks
University of Coimbra, CISUC/LASI, DEI, Coimbra, Portugal
Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability
Mar 26, 2026Jiaming Liang, Chi-Man PunNeural Network Robustness Adversarial Robustness
University of Macau, Macau, China
Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
Mar 26, 2026Shiji Zhao, Shukun Xiong, Maoxun Yuan +6Infrared Object Detection Adversarial Robustness
Institute of Artificial Intelligence, Beihang University, No.37 Xueyuan Road, Haidian District, Beijing 100191, P.R. China. · Security Department, Alibaba Group, Hangzhou 310056, China. · School of Computer Science, Nankai University, China. +2
Attack Assessment and Augmented Identity Recognition for Human Skeleton Data
Mar 25, 2026Joseph G. Zalameda, Megan A. Witherow, Alexander M. Glandon +2Adversarial Robustness Adversarial Training
Dept. of ECE, Old Dominion University, Norfolk, VA, USA · Dept. of Computer Science, Amherst College, Hampshire County, MA, USA
Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
Mar 25, 2026Yunrui Yu, Hang Su, Jun ZhuLoss Landscape Sharpness Adversarial Robustness
1Tsinghua University, Beijing, China.
Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection
Mar 24, 2026Rodrigo F. L. Lassance, Jasper De BockAdversarial Robustness Classification
Foundations Lab for imprecise probabilities (FLip), Ghent University, Ghent, Belgium · Statistics Dept., Federal University of São Carlos, São Carlos, São Paulo, Brazil · Institute of Mathematic and Computer Sciences, University of São Paulo, São Carlos, São Paulo, Brazil
Robustness Quantification and Uncertainty Quantification: Comparing Two Methods for Assessing the Reliability of Classifier Predictions
Mar 24, 2026Adrián Detavernier, Jasper De BockUncertainty Quantification Adversarial Robustness
Foundations Lab for imprecise probabilities, Ghent University, Belgium
Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
Mar 23, 2026Matías Pizarro, Raghavan Narasimhan, Jonas Killian +1Adversarial Robustness Robust ASR
Faculty of Computer Science, Ruhr University Bochum, Bochum, Germany
Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
Mar 23, 2026Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty +2Adversarial Robustness Neural Operators
Department of Nuclear, Plasma & Radiological Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA · Department of Applied Mechanics, Indian Institute of Technology Delhi, New Delhi 110016, India · National Center for Supercomputing Applications, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA
DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation
Mar 23, 2026Binhong Tan, Zhaoxin Wang, Handing WangSafe T2I Generation T2I Diffusion Models
Xidian University Xi’an, China
Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
Mar 23, 2026Chengyin Hu, Yikun Guo, Yuxian Dong +7Adversarial Patch Attacks Physical Adversarial Attacks
China University of Petroleum-Beijing at Karamay, No. 355, Anding Road, Karamay, 834000, Xinjiang, China. · Guangdong University of Technology, Guangzhou, Guangdong, China. · Tianjin University, Tianjin, China. +1
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
Mar 21, 2026Shouqiao Wang, Marcello Politi, Samuele Marro +1AI Agent Security Automated Red Teaming
Columbia University · dAI Team, Ethereum Foundation · University of Oxford

Apr 3, 2026J/K move · Enter open · S save

Adversarial Robustness of Deep State Space Models for Forecasting

Sribalaji C. Anand, George J. Pappas

Department of Electrical and Systems Engineering, University of Pennsylvania, United States · KTH Royal Institute of Technology, Sweden

Adversarial Robustness State Space Models Black-Box Adversarial Attacks

Open paper AskPDF arXiv

State-space model (SSM) for time-series forecasting have demonstrated strong empirical performance on benchmark datasets, yet their robustness under adversarial perturbations is poorly understood. We address this gap through a control-theoretic lens, focusing on the recently proposed Spacetime SSM forecaster. We first establish that the decoder-only Spacetime architecture can represent the optimal Kalman predictor when the underlying data-generating process is autoregressive - a property no other SSM possesses. Building on this, we formulate robust forecaster design as a Stackelberg game against worst-case stealthy adversaries constrained by a detection budget, and solve it via adversarial training. We derive closed-form bounds on adversarial forecasting error that expose how open-loop instability, closed-loop instability, and decoder state dimension each amplify vulnerability - offering actionable principles towards robust forecaster design. Finally, we show that even adversaries with no access to the forecaster can nonetheless construct effective attacks by exploiting the model's locally linear input-output behavior, bypassing gradient computations entirely. Experiments on the Monash benchmark datasets highlight that model-free attacks, without any gradient computation, can cause at least 33% more error than projected gradient descent with a small step size.