Adversarial Attacks

Follow this topic Ask about this topic

Adversarial attacks study how deliberately chosen inputs, training data, model parameters, or system interactions can make AI systems fail or behave as intended by an attacker. Common approaches include gradient-based perturbations, black-box query and evolutionary search, generative or semantic changes, physical patches and sensor interference, and poisoning or backdoors. Work spans image, language, audio, graph, and time-series models as well as federated learning, recommenders, robotics, and AI agents, with evaluations on benchmarks and increasingly realistic deployment settings. A central tension is that attacks must be effective and stealthy under practical constraints, while defenses and benchmarks must keep pace with adaptive threats and distinguish digital robustness from real-world resilience.

Latest papers

451 papers54 papers in the last four weeks, up 69% on the four weeks before. 0.3% of all new papers.

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning
Apr 16, 2026Francesco Diana, Chuan Xu, André Nusser +1Gradient Inversion Attacks Adversarial Attacks
Université Côte d’Azur, France · Inria, France · CNRS, France +1
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
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
INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression
Apr 13, 2026Gamze Kirman Tokgoz, Onat Gungor, Tajana Rosing +1Adversarial Attacks Time Series Forecasting
San Diego State University, San Diego, CA, USA · University of California, San Diego, CA, USA
Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
Apr 13, 2026Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam +2Certified Robustness Neural Network Verification
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich Data Science Institute, Technical University of Munich · Munich Center for Machine Learning, Germany +1
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
Apr 11, 2026Jose Efraim Aguilar Escamilla, Haoyang Hong, Jiawei Li +4Markov Decision Processes Adversarial Attacks
Oregon State University, OR, USA · University of Illinois Urbana–Champaign, IL, USA · Princeton University, NJ, USA +1
Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Clouds
Apr 10, 2026Gayathry Chandramana Krishnan Nampoothiry, Raghuram Venkatapuram, Anirban Ghosh +1Adversarial Attacks Adversarial Examples
University of North Florida, Jacksonville, USA
Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control
Apr 9, 2026Julian Quick, Marcus Binder Nilsen, Andreas Bechmann +2Robust Control Adversarial Attacks
Department of Wind and Energy Systems, Technical University of Denmark, Roskilde, Denmark · Department of Engineering Technology and Didactics, Technical University of Denmark, Ballerup, Denmark
SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
Apr 9, 2026Wenli Zhang, Xianglong Shi, Sirui Zhao +5Adversarial Attacks Audio-Driven Facial Animation
Preference Redirection via Attention Concentration: An Attack on Computer Use Agents
Apr 9, 2026Dominik Seip, Matthias HeinAdversarial Attacks Adversarial Attacks on VLMs
Tübingen AI Center, University of Tübingen
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
Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasion
Apr 8, 2026Miguel A. DelaCruz, Patricia Mae Santos, Rafael T. NavarroAdversarial Attacks Physical Adversarial Attacks
College of Computer Studies, De La Salle University, Manila, Philippines
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
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
Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality
Apr 7, 2026Yanming Xiu, Zhengyuan Jiang, Neil Zhenqiang Gong +1Augmented Reality VLM Robustness
Duke University
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
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
Apr 5, 2026Siyuan Li, Zehao Liu, Xi Lin +6LLM Security Adversarial Robustness of Language Models
School of Computer Science, Shanghai Jiao Tong University · Department of Computer Science, University of Illinois Urbana-Champaign · Big Data Institute, Central South University
A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
Apr 5, 2026Tianle Chen, Deepti GhadiyaramAdversarial Attacks on Unified Multimodal Models Adversarial Attacks
Department of Computer Science, Boston University
Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs
Apr 4, 2026Andrew Wheeler, Kshitiz Aryal, Maanak GuptaAdversarial Attacks Malware Detection
Department of Computer Science, Tennessee Tech University, Cookeville, USA · School of Interdisciplinary Informatics, University of Nebraska Omaha, Omaha, USA
Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks
Apr 4, 2026Manoj ParmarState Space Models Adversarial Attacks
SovereignAI Security Labs, Bengaluru, India
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
Apr 3, 2026Yuheng Zhang, Mingyue Huo, Minghao Zhu +2Adversarial Attacks Adversarial Text Attacks
UIUC · Independent Researcher · University of Massachusetts Amherst
Street-Legal Physical-World Adversarial Rim for License Plates
Apr 2, 2026Nikhil Kalidasu, Sahana GanapathyAdversarial Attacks Physical Adversarial Attacks
The University of Texas at Austin, Austin TX 78705, USA
Safety, Security, and Cognitive Risks in World Models
Apr 1, 2026Manoj ParmarAdversarial Attacks on World Models World Models
SovereignAI Security Labs, Bengaluru, India
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
Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detection
Apr 1, 2026Yiming Zhang, Weibo Qin, Feng WangAdversarial Attacks Adversarial Patch Attacks
Key Laboratory for Information Science of Electromagnetic Waves (MoE), School of Information Science and Technology, Fudan University, Shanghai 200433, China
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
Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
Apr 1, 2026Halima Bouzidi, Haoyu Liu, Yonatan Gizachew Achamyeleh +2Adversarial Attacks Multi-Object Tracking
University of California, Irvine, CA, USA
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
With a Little Help From My Friends: Collective Manipulation in Risk-Controlling Recommender Systems
Mar 30, 2026Giovanni De Toni, Cristian Consonni, Erasmo Purificato +2Recommender Systems Adversarial Attacks
Fondazione Bruno Kessler, Italy · European Commission, Joint Research Centre (JRC)
From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera
Mar 30, 2026Victoria Leonenkova, Ekaterina Shumitskaya, Dmitriy Vatolin +1Adversarial Attacks Adversarial Patch Attacks
Lomonosov MSU, Moscow, Russia · AI Center, Lomonosov MSU, IAI MSU, Moscow, Russia

Apr 16, 2026J/K move · Enter open · S save

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning

Francesco Diana, Chuan Xu, André Nusser, Giovanni Neglia

Université Côte d’Azur, France · Inria, France · CNRS, France+1

Gradient Inversion Attacks Adversarial Attacks Federated Learning

Open paper AskPDF arXiv

Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients' shared gradients. Gradients aggregate contributions from multiple records and existing attacks may fail to disentangle them, yielding incorrect reconstructions with no intrinsic way to certify success. In vision and language, attackers may fall back on human inspection to judge reconstruction plausibility, but this is far less feasible for numerical tabular records, fueling the impression that tabular data is less vulnerable. We challenge this perception by proposing a verifiable gradient inversion attack (VGIA) that provides an explicit certificate of correctness for reconstructed samples. Our method adopts a geometric view of ReLU leakage: the activation boundary of a fully connected layer defines a hyperplane in input space. VGIA introduces an algebraic, subspace-based verification test that detects when a hyperplane-delimited region contains exactly one record. Once isolation is certified, VGIA recovers the corresponding feature vector analytically and reconstructs the target via a lightweight optimization step. Experiments on tabular benchmarks with large batch sizes demonstrate exact record and target recovery in regimes where existing state-of-the-art attacks either fail or cannot assess reconstruction fidelity. Compared to prior geometric approaches, VGIA allocates hyperplane queries more effectively, yielding faster reconstructions with fewer attack rounds.