Adversarial Perturbations

Follow this topic Ask about this topic

Adversarial perturbation research studies how small, structured, or physically realizable changes to inputs alter model predictions and behavior. Common approaches include gradient-based attacks such as FGSM and PGD, universal and transfer attacks, query-efficient black-box search, and attacks designed for text, audio, 3D data, or physical settings. Defenses include adversarial training, input purification, detection, and robustness certification, while protective perturbations also aim to preserve privacy or limit unauthorized use of images and videos. A central challenge is that success on fixed benchmarks may not predict performance after compression, resizing, environmental change, or closed-loop deployment, and stronger protection often trades off against visual quality, utility, or attack transferability.

Latest papers

105 papers10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
Feb 22, 2026Yiran Qiao, Yiren Lu, Yunlai Zhou +43D Gaussian Splatting 3D Reconstruction
Case Western Reserve University, Cleveland OH 44106, USA
Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation
Feb 19, 2026Bogdan Kostić, Conor Fallon, Julian Risch +1Prompt Sensitivity LLM Evaluation
Berliner Hochschule für Technik (BHT) - Luxemburger Straße 10, 13467 Berlin · deepset GmbH - Zinnowitzer Straße 1, 10115 Berlin
Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
Feb 16, 2026Chanhui Lee, Donggyu Choi, Seunghyun Shin +2Adversarial Robustness Adversarial Perturbations
POSTECH · GIST · Yonsei University
Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks
Feb 6, 2026Christof Duhme, Florian Eilers, Xiaoyi JiangAdversarial Attacks Adversarial Perturbations
Department of Computer Science University of Münster Münster, Germany
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
Jan 18, 2026Jinwei Hu, Shiyuan Meng, Yi Dong +1Adversarial Attacks Adversarial Robustness
University of Liverpool, Liverpool, UK · Shanghai Artificial Intelligence Laboratory, Shanghai, China
Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
Dec 4, 2025Marco Pintore, Maura Pintor, Dimosthenis Karatzas +1Visual Question Answering VLM Robustness
University of Cagliari, Italy · CINI, Italy · Computer Vision Center, UAB, Spain
Enhancing Adversarial Transferability through Block Stretch and Shrink
Nov 21, 2025Quan Liu, Feng Ye, Chenhao Lu +4Adversarial Attacks Adversarial Perturbations
SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
Nov 12, 2025Tairan Huang, Yulin Jin, Junxu Liu +2Adversarial Attacks Adversarial Perturbations
The Hong Kong Polytechnic University Hong Kong, China
Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning
Nov 12, 2025Jian Wang, Hong Shen, Chan-Tong LamAdversarial Attacks Backdoor Attacks in Federated Learning
Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China · School of Cyberspace Security, Guangzhou University of Software, Guangzhou, China · School of Engineering and Technology, Central Queensland University, Australia
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Oct 19, 2025Mansi Phute, Matthew Hull, Haoran Wang +6Adversarial Attacks Adversarial Perturbations
Georgia Institute of Technology, USA · Technology Innovation Institute, UAE
On the Interaction of Compressibility and Adversarial Robustness
Jul 23, 2025Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli +1Neural Network Robustness Adversarial Robustness
Department of Computing, Imperial College London, UK · Department of Information Technology, Uppsala University, Sweden · INRIA, CNRS, Département d’Informatique de l’Ecole Normale Supérieure / PSL, France
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
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
Feb 6, 2025Akansha Kalra, Basavasagar Patil, Guanhong Tao +1Adversarial Robustness Adversarial Imitation Learning
University of Utah
Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models
Dec 11, 2024Hee-Seon Kim, Minbeom Kim, Seokil Ham +1VLM Robustness Adversarial Attacks on VLMs
School of Electrical Engineering, KAIST, Daejeon 34141, Republic of Korea
Stealthy Multi-Task Adversarial Attacks
Nov 26, 2024Jiacheng Guo, Tianyun Zhang, Lei Li +3Adversarial Attacks Adversarial Perturbations
Cleveland State University, Cleveland, OH 44115, USA · University of Wisconsin-Madison, Madison, WI 53706, USA · Western Digital Research, San Jose, CA 95119, USA

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

DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering

Yiran Qiao, Yiren Lu, Yunlai Zhou, Rui Yang+3

Case Western Reserve University, Cleveland OH 44106, USA

3D Gaussian Splatting 3D Reconstruction Adversarial Robustness Adversarial Perturbations

Open paper AskPDF arXiv

3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, where imperceptible yet consistent perturbations can drastically degrade rendering quality, increase training and rendering time, and inflate memory usage, even leading to server denial-of-service. In our work, to mitigate this issue, we begin by analyzing the distinct behaviors of adversarial perturbations in the low- and high-frequency components of input images using wavelet transforms. Based on this observation, we design a simple yet effective frequency-aware defense strategy that reconstructs training views by filtering high-frequency noise while preserving low-frequency content. This approach effectively suppresses adversarial artifacts while maintaining the authenticity of the original scene. Notably, it does not significantly impair training on clean data, achieving a desirable trade-off between robustness and performance on clean inputs. Through extensive experiments under a wide range of attack intensities on multiple benchmarks, we demonstrate that our method substantially enhances the robustness of 3DGS without access to clean ground-truth supervision. By highlighting and addressing the overlooked vulnerabilities of 3D Gaussian Splatting, our work paves the way for more robust and secure 3D reconstructions.