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.

FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods
Apr 22, 2026Chao Pan, Xin YaoAdversarial Training Adversarial Robustness
Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · School of Data Science, Lingnan University, Hong Kong, China
Benign Overfitting in Adversarial Training for Vision Transformers
Apr 21, 2026Jiaming Zhang, Meng Ding, Shaopeng Fu +2Adversarial Training Neural Network Generalization
Division of CEMSE, King Abdullah University of Science and Technology · School of Statistics, Renmin University of China · Department of Computer Science and Engineering, State University of New York at Buffalo +1
How Adversarial Environments Mislead Agentic AI?
Apr 20, 2026Zhonghao Zhan, Huichi Zhou, Zhenhao Li +3Adversarial Robustness AI Agent Evaluation
Imperial College London
MetaCloak-JPEG: JPEG-Robust Adversarial Perturbation for Preventing Unauthorized DreamBooth-Based Deepfake Generation
Apr 20, 2026Tanjim Rahaman Fardin, S M Zunaid Alam, Mahadi Hasan Fahim +1Adversarial Robustness Diffusion-Based Image Generation
Computer Science and Engineering BRAC University Dhaka, Bangladesh
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
Apr 18, 2026Jiayuan Liu, Shiyi Du, Weihua Du +2Multi-Agent LLM Systems Adversarial Robustness
Carnegie Mellon University · Foundations of Cooperative AI Lab (FOCAL) · Adelaide University
CCAR: Intrinsic Robustness as an Emergent Geometric Property
Apr 18, 2026Akash Samanta, Manish Pratap Singh, Debasis ChaudhuriDisentangled Representation Learning Representation Learning
Techno India University, Salt Lake, Kolkata, India · DRDO Young Scientist Laboratory - CT, Chennai, India
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
Apr 17, 2026Geunyoung Jung, Soohong Kim, Inseok Kong +1Point Cloud Classification Adversarial Robustness
Department of Artificial Intelligence, University of Seoul, South Korea · Department of Geo Informatics, University of Seoul, South Korea
Beyond Attack Success Rate: A Multi-Metric Evaluation of Adversarial Transferability in Medical Imaging Models
Apr 16, 2026Emily Curl, Kofi Ampomah, Md Erfan +1Adversarial Robustness Medical Image Classification
The authors are with The University of Alabama, Tuscaloosa, USA.
Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
Apr 15, 2026Fortunatus Aabangbio Wulnye, Justice Owusu Agyemang, Kwame Opuni-Boachie Obour Agyekum +3IoT Intrusion Detection Adversarial Robustness
Department of Telecommunication, Kwame Nkrumah University of Science and Technology (KNUST), Kumasi, Ghana
TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement
Apr 15, 2026Xinxin Fan, Wenxiong Chen, Quanliang Jing +4Adversarial Robustness Adversarial Attacks
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Dalian University of Technology +1
Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators
Apr 14, 2026Samrendra Roy, Souvik Chakraborty, Syed Bahauddin AlamAdversarial Robustness Neural Operators
Department of Nuclear, Plasma, and Radiological Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA · Department of Applied Mechanics, Indian Institute of Technology Delhi, New Delhi, India · National Center for Supercomputing Applications, University of Illinois Urbana-Champaign, Urbana, IL, USA
Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images
Apr 14, 2026Haoyang Jiang, Mingyang Yi, Shaolei Zhang +4Adversarial Attacks on AI-Generated Image Detectors AI-Generated Image Detection
Renmin University of China, Beijing, China · Tencent Inc., Shenzhen, China
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
Apr 14, 2026Wenyun Li, Zheng Zhang, Dongmei Jiang +2Adversarial Training Adversarial Robustness
Harbin Institute of Technology, Shenzhen · Pengcheng Laboratory · Pazhou Laboratory (Huangpu)
GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees
Apr 14, 2026Arya Shah, Kaveri Visavadiya, Manisha PadalaAdversarial Robustness Certified Robustness
IIT Gandhinagar
Robust Semi-Supervised Temporal Intrusion Detection for Adversarial Cloud Networks
Apr 14, 2026Anasuya Chattopadhyay, Daniel Reti, Hans D. SchottenNetwork Intrusion Detection Cybersecurity
German Research Center for Artificial Intelligence (DFKI), Germany · RPTU University Kaiserslautern-Landau, Germany
RACF: A Resilient Autonomous Car Framework with Object Distance Correction
Apr 14, 2026Chieh Tsai, Hossein Rastgoftar, Salim HaririAutonomous Driving Adversarial Robustness
Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, USA · Department of Aerospace and Mechanical Engineering, University of Arizona, Tucson, AZ, USA
Learning Robustness at Test-Time from a Non-Robust Teacher
Apr 13, 2026Stefano Bianchettin, Giulio Rossolini, Giorgio ButtazzoAdversarial Robustness Test-Time Adaptation
Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Study, Via Moruzzi, 1, Pisa, 56124, Tuscany, Italy
QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits
Apr 13, 2026Navid Azimi, Aditya Prakash, Yao Wang +1Adversarial Robustness Hybrid Quantum-Classical ML
Department of Computer Science, Emory University, 201 Dowman Drive, Atlanta, 30322, GA, USA. · Department of Physics, Emory University, 201 Dowman Drive, Atlanta, 30322, GA, USA.
DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion Models
Apr 13, 2026Qinghui Gong, Zhengchun Zhou, Hua Meng +2Diffusion Model Unlearning T2I Diffusion Models
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan, China · School of Mathematics, Southwest Jiaotong University, Chengdu, Sichuan, China
Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
Apr 12, 2026Wei Zhang, Xinyu Chang, Xiao Li +2Adversarial Robustness Adversarial Examples
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China. · School of Software, Tsinghua University, Beijing 100084, China. · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China. +2
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
Apr 9, 2026Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1Adversarial Robustness Certified Robustness
Foundation for Reasearch and Technology - Hellas, Heraklion, Greece · University of Crete, Heraklion, Greece · Catalan Institution for Research and Advanced Studies, Barcelona, Spain +1
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
Apr 9, 2026Hengyu An, Minxi Li, Jinghuai Zhang +6Multi-Agent System Security AI Agent Security Benchmarks
Zhejiang University · State Key Laboratory of Internet Architecture, Tsinghua University · University of California, Los Angeles +2
Compression as an Adversarial Amplifier Through Decision Space Reduction
Apr 8, 2026Lewis Evans, Harkrishan Jandu, Zihan Ye +2Adversarial Attacks Adversarial Examples
University of Nottingham, Nottingham, United Kingdom · University of Chinese Academy of Sciences, Beijing, China · Xiamen University, Xiamen, China +1
MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors
Apr 8, 2026Xiaotian Luo, Xun Jiang, Jiangcheng WuAdversarial Robustness of Language Models Medical LLMs
Shanda Group
The Deployment Gap in AI Media Detection: Platform-Aware and Visually Constrained Adversarial Evaluation
Apr 7, 2026Aishwarya Budhkar, Trishita Dhara, Siddhesh ShethAdversarial Attacks on AI-Generated Image Detectors AI-Generated Image Detection
Ace Rent a Car
Extending ZACH-ViT to Robust Medical Imaging: Corruption and Adversarial Stress Testing in Low-Data Regimes
Apr 7, 2026Athanasios Angelakis, Marta Gomez-BarreroVision Transformer Medical Image Classification
BioML Lab, RI CODE, UniBw, Munich, Germany · AUMC, Amsterdam, Netherlands
Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
Apr 7, 2026Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi +4Adversarial Robustness Adversarial Attacks
CERN, Geneva, Switzerland · RWTH Aachen University, Aachen, Germany · DESY, Hamburg, Germany
Adversarial Robustness Analysis of Cloud-Assisted Autonomous Driving Systems
Apr 6, 2026Maher Al Islam, Amr S. El-WakeelAdversarial Attacks on Object Detectors Adversarial Robustness
Lane Department of Computer Science and Electrical Engineering, West Virginia University, WV, USA
SafeCtrl: Region-Aware Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
Apr 5, 2026Lingyun Zhang, Yu Xie, Zhongli Fang +2Safe T2I Generation Adversarial Robustness
School of Computer Science and Technology, Fudan University, China · Institute of Big Data, Fudan University, China · Nanjing University of Information Science and Technology, China
Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
Apr 3, 2026Solon Falas, Markos Asprou, Charalambos Konstantinou +1False Data Injection Attacks Adversarial Robustness
KIOS Center of Excellence, University of Cyprus · CEMSE, King Abdullah University of Science and Technology (KAUST) · Department of Electrical and Computer Engineering, University of Cyprus

Apr 22, 2026J/K move · Enter open · S save

FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods

Chao Pan, Xin Yao

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · School of Data Science, Lingnan University, Hong Kong, China

Adversarial Training Adversarial Robustness

Open paper AskPDF arXiv

Fast Adversarial Training (FastAT) seeks to achieve adversarial robustness at a fraction of the computational cost incurred by standard multi-step methods such as PGD-AT. Although numerous FastAT techniques have been proposed in recent years, fair comparison among them remains elusive. Existing benchmarks and public leaderboards typically permit diverse model architectures, varying training configurations, and external data sources, making it unclear whether reported improvements reflect genuine algorithmic advances or merely more favorable experimental conditions. To address this problem, we introduce the FastAT Benchmark, a controlled evaluation framework built on three core design principles: unified architecture requirements, standardized training settings, and strict prohibition of external or synthetic data. The benchmark implements over twenty representative FastAT methods within a single codebase, enabling direct and reproducible comparison. Each method is assessed through a dual-metric evaluation framework that measures both adversarial robustness (accuracy under PGD, AutoAttack, and CR Attack) and computational cost (GPU training time and peak memory footprint). Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet provide reliable baseline measurements and reveal that well-designed single-step methods can match or surpass PGD-AT robustness at substantially lower cost, while no single method dominates across all evaluation dimensions. The complete benchmark, including source code, configuration files, and experimental results, is publicly available to support transparent and fair evaluation of future FastAT research.