Consistent Adversarial Attacks

Follow this topic Ask about this topic

Consistent adversarial attacks study perturbations that retain their intended effect across repeated attempts, viewpoints, time, models, or physical conditions, sometimes while preserving the ground-truth label. Approaches include label-preserving error analysis, temporal and cross-view optimization, transferable attacks using surrogate models, and physical-attack methods that model lighting, materials, or object-camera trajectories. Evaluation increasingly looks beyond single-run attack success to repeated success, transfer across models, perceptual quality, and downstream effects on tasks such as tracking, planning, and 3D perception. A central tension is making attacks effective and consistent without making them perceptible or unrealistic, while ensuring robustness tests reflect real deployment conditions rather than isolated benchmarks.

Latest papers

17 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models
Oct 11, 2026Song Xia, Meiwen Ding, Chenqi Kong +2Adversarial Attacks Physical Adversarial Attacks
Nanyang Technological University · National University of Singapore · Pengcheng Lab
One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs
Sep 27, 2026Sen Nie, Jie Zhang, Zhongqi Wang +2Adversarial Attacks on VLMs Adversarial Attacks on LLMs
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences.
Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
Aug 21, 2026Qi Song, Ziyuan Luo, Haoliang Han +1Adversarial Attacks Adversarial Perturbations
Department of Computer Science, Hong Kong Baptist University, Hong Kong, China · Renjie Group, Hong Kong Baptist University
IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack
Aug 9, 2026Yi Pan, Jun-Jie Huang, Tianrui Liu +3Adversarial Attacks Transfer-Based Adversarial Attacks
College of Computer Science and Technology
Fast LapSum: Exact Differentiable Top- $k$ at Million Scale
Aug 7, 2026Jakub Antczak, Joanna Wojciechowicz, Kamil Książek +3Differentiable Programming Differentiable Optimization
Wrocław University of Science and Technology Wrocław, Poland · Centre for Credible Artificial Intelligence Warsaw University of Technology Warsaw, Poland · Jagiellonian University Kraków, Poland
QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
Jul 31, 2026Xiang Chen, Yingying Zhao, Chao Li +7VLM Robustness Adversarial Attacks on VLMs
IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks
Jul 29, 2026Mengqi He, Jing ZhangAdversarial Attacks Transfer-Based Adversarial Attacks
School of Computing, College of Systems & Society · The Australian National University, Canberra, ACT, Australia
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
Jul 16, 2026Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi SadeghzadehAdversarial Robustness Black-Box Adversarial Attacks
Department of Computer Engineering Sharif University of Technology
Binary Iterative Method for Non-targeted Adversarial Attack
Jul 5, 2026Naman Goyal, Milan ChaudhariAdversarial Attacks Consistent Adversarial Attacks
Indian Institute of Technology, Ropar
Learning to Evade: Adaptive Attacks on Audio Watermarking
Jun 21, 2026Weikang Ding, Hanqing Guo, Rui Duan +4Watermark Removal Audio Watermarking
University of Missouri-Kansas City, USA · University of Hawaii at Manoa, USA · University of South Florida, USA +2
The Great Pretender: A Stochasticity Problem in LLM Jailbreak
May 14, 2026Jean-Philippe Monteuuis, Cong Chen, Jonathan PetitLLM Safety Benchmarks LLM Evaluation
Qualcomm Technologies, Inc.
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
R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting
Mar 27, 2026Tianrui Lou, Siyuan Liang, Jiawei Liang +2Physical Adversarial Attacks Consistent Adversarial Attacks
School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen 518107, China · School of Computing, National University of Singapore, 117417, Singapore · School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen 518107, China
Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications
Mar 14, 2026Philip Bechtle, Lucie Flek, Philipp Alexander Jung +7Adversarial Robustness Adversarial Perturbations
Institute of Physics, University of Bonn, Germany. · Bonn-Aachen Institute of Technology, University of Bonn, Germany. · Physics Institute III A, RWTH Aachen University, Germany. +1
Advantage-based Temporal Attack in Reinforcement Learning
Feb 23, 2026Shenghong HeAttention-Based Adversarial Attacks Adversarial Attacks
the School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models
Feb 21, 2026Zhixiang Guo, Siyuan Liang, Andras Balogh +4Adversarial Attacks on World Models Adversarial Attacks
Nanyang Technological University · University of Szeged
On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
Jun 14, 2025Matteo Vilucchio, Lenka Zdeborová, Bruno LoureiroAdversarial Attacks Adversarial Robustness
Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL) · Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL) · Département d’Informatique, École Normale Supérieure - PSL & CNRS, France

Oct 11, 2026J/K move · Enter open · S save

Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models

Song Xia, Meiwen Ding, Chenqi Kong, Wenhan Yang+1

Nanyang Technological University · National University of Singapore · Pengcheng Lab

Adversarial Attacks Physical Adversarial Attacks Adversarial Attacks on World Models Consistent Adversarial Attacks Video World Models

Open paper AskPDF arXiv

World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely underexplored. We study whether a single physical adversarial texture can mislead the victim model across different real-world scenarios where observing viewpoints vary along uncontrolled object--camera trajectories. We identify that heterogeneous video semantics and trajectories induce poorly aligned gradients for optimizing the adversarial texture. To address that, we propose the Trajectory-aware adversarial Alignment and Refinement Attack (TARA), which incorporates trajectory-aware optimization to capture the evolving geometric variations of a printed texture under real-world scenarios. To improve cross-instance optimization compatibility, TARA incorporates trajectory-aware contrastive alignment to encourage attacked representations from diverse video--trajectory instances to approach a shared adversarial region and then performs trajectory-aware task refinement to translate the aligned representation into task-level prediction errors. For reproducible evaluation, we develop a geometry-grounded tracking pipeline that provides physically plausible adversarial regions with temporally consistent trajectories on EPIC-KITCHENS-100 and Something-Something V2. We further collect real-world print-and-recapture videos to validate attack effectiveness under physical deployment conditions. Together, the annotated benchmarks and real-world captured data form a reproducible testbed for future evaluation. Notably, our results reveal that a single printable adversarial texture can persistently disrupt world models and video understanding models under physical conditions, highlighting the fundamental security challenge.