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.

Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces
Mar 6, 2026Eitan Shaar, Ariel Shaulov, Yalcin Tur +2Adversarial Attacks Adversarial Examples
Independent Researcher · Tel-Aviv University · Stanford University +3
Identifying Adversary Characteristics from an Observed Attack
Mar 5, 2026Soyon Choi, Scott Alfeld, Meiyi MaQuery Identifiability Adversarial Attacks
Vanderbilt University Nashville, TN 37240 · Amherst College Amherst, MA 01002
Beyond the Patch: Exploring Vulnerabilities of Visuomotor Policies via Viewpoint-Consistent 3D Adversarial Object
Mar 5, 2026Chanmi Lee, Minsung Yoon, Woojae Kim +2Adversarial Attacks Physical Adversarial Attacks
The School of Computing at the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141, Republic of Korea
Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
Mar 4, 2026Haoyu Liu, Dingcheng Li, Lukas Rutishauser +1Adversarial Training Multimodal Robustness
UC Berkeley, IEOR & BAIR · Google · Google Deepmind
VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models
Mar 2, 2026Duoxun Tang, Dasen Dai, Jiyao Wang +3Adversarial Attacks on VLMs Adversarial Attacks
Shenzhen International Graduate School, Tsinghua University · The Chinese University of Hong Kong, Hong Kong SAR · McGill University +3
AMDS: Attack-Aware Multi-Stage Defense System for Network Intrusion Detection with Two-Stage Adaptive Weight Learning
Mar 1, 2026Oluseyi Olukola, Nick RahimiNetwork Intrusion Detection Adversarial Robustness
School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, USA
Analyzing Physical Adversarial Example Threats to Machine Learning in Election Systems
Feb 28, 2026Khaleque Md Aashiq Kamal, Surya Eada, Aayushi Verma +4Adversarial Attacks Adversarial Examples
Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA · Voting Technology Center, University of Connecticut, Storrs, CT, USA · Department of Computer Science and Statistics, University of Rhode Island, Kingston, RI, USA
Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
Feb 25, 2026Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde +4Adversarial Attacks Adversarial Robustness
University of Texas at San Antonio San Antonio, TX, USA
Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images!
Feb 25, 2026Zihang Zou, Boqing Gong, Liqiang WangAdversarial Attacks on Diffusion Models Adversarial Attacks
University of Central Florida · Boston University
Poisoned Acoustics
Feb 25, 2026Harrison DahmeAdversarial Attacks Data Poisoning Attacks
CTO and Partner, Hack VC
Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
Feb 23, 2026Yihang Tao, Senkang Hu, Haonan An +3Adversarial Attacks Cooperative Perception
Hong Kong JC STEM Lab of Smart City · City University of Hong Kong
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
Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation Systems
Feb 23, 2026Xingyu Shen, Tommy Duong, Xiaodong An +6Adversarial Attacks Physical Adversarial Attacks
Reality Inc. · Duke University · UC Berkeley +3
PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
Feb 23, 2026Hefei Mei, Zirui Wang, Chang Xu +2Attention-Based Adversarial Attacks Adversarial Attacks on VLMs
City University of Hong Kong · The University of Sydney
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Feb 22, 2026Wei Tao, Yang Dai, Jincai Huang +1Adversarial Attacks Adversarial Examples
Laboratory for Big Data and Decision, National University of Defense and Technology, China · Academy of Military Science, China · Hefei Institute of Technology, China
When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks
Feb 21, 2026Shenyang Chen, Liuwan ZhuAdversarial Attacks Representation Drift
Google · Electrical and Computer Engineering Department, University of Hawai‘i at Mānoa
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
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
Feb 20, 2026Rishabh Tiwari, Aditya Tomar, Udbhav Bamba +5Process Reward Models Reward Hacking
UC Berkeley · Transmute AI · ICSI +1
Generating adversarial inputs for a graph neural network model of AC power flow
Feb 20, 2026Robert ParkerNeural Surrogate Modeling Graph Neural Networks
Los Alamos National Laboratory, Los Alamos, NM, USA
A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion
Feb 20, 2026Yu Bai, Zhe Wang, Jiarui Zhang +3Adversarial Robustness Adversarial Attacks
Northwest Institute of Nuclear Technology, Xi’an, 710024, P.R. China
TFL: Targeted Bit-Flip Attack on Large Language Model
Feb 19, 2026Jingkai Guo, Chaitali Chakrabarti, Deliang FanAdversarial Attacks Adversarial Attacks on LLMs
School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA
Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems
Feb 18, 2026Jialiang Fan, Shixiong Jiang, Mengyu Liu +1Adversarial Attacks Black-Box Adversarial Attacks
University of Notre Dame, Notre Dame, IN, USA. · Washington State University Tri-Cities, Richland, WA, USA.
Benchmarking Adversarial Robustness and Adversarial Training Strategies for Object Detection
Feb 18, 2026Alexis Winter, Jean-Vincent Martini, Romaric Audigier +2Adversarial Attacks on Object Detectors Adversarial Robustness
Universit´e Paris-Saclay, CEA, List, F-91191, Palaiseau, France.
Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis
Feb 18, 2026Scott ThorntonAdversarial Attacks Adversarial Attacks on LLMs
Is Mamba Reliable for Medical Imaging?
Feb 16, 2026Banafsheh Saber Latibari, Najmeh Nazari, Daniel Brignac +3Adversarial Robustness Mamba
Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, USA · Department of Electrical and Computer Engineering, University of California, Davis, CA, USA · Department of Computer Engineering and Computer Science, California State University, Long Beach, Long Beach, CA, USA
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
Feb 6, 2026Kichang Lee, Jaeho Jin, JaeYeon Park +2Adversarial Attacks Federated Learning
Yonsei University · Dankook 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
Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
Feb 6, 2026Florian Eilers, Christof Duhme, Xiaoyi JiangAdversarial Attacks Neural Network Robustness
Department of Computer Science University of Münster Münster, Germany
Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
Feb 4, 2026Jaehyun Kwak, Nam Cao, Boryeong Cho +3Adversarial Attacks on VLMs Adversarial Attacks
KAIST · KENTECH
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Jan 30, 2026Zhixiang Zhang, Zesen Liu, Yuchong Xie +2Adversarial Attacks LLM Agent Security
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · Fudan University

Mar 6, 2026J/K move · Enter open · S save

Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces

Eitan Shaar, Ariel Shaulov, Yalcin Tur, Gal Chechik+1

Independent Researcher · Tel-Aviv University · Stanford University+3

Adversarial Attacks Adversarial Examples Transfer-Based Adversarial Attacks

Open paper AskPDF arXiv

Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under

\ell_\infty

\ell_2

constraints. While effective in white-box settings, pixel-space optimization often produces high-frequency, texture-like noise that is brittle to common preprocessing (e.g., resizing and cropping) and transfers poorly across architectures. We propose

\textbf{LTA}

(

\textbf{L}

atent

\textbf{T}

ransfer

\textbf{A}

ttack), a transfer-based attack that instead optimizes perturbations in the latent space of a pretrained Stable Diffusion VAE. Given a clean image, we encode it into a latent code and optimize the latent representation to maximize a surrogate classifier loss, while softly enforcing a pixel-space

\ell_\infty

budget after decoding. To improve robustness to resolution mismatch and standard input pipelines, we incorporate Expectation Over Transformations (EOT) via randomized resizing, interpolation, and cropping, and apply periodic latent Gaussian smoothing to suppress emerging artifacts and stabilize optimization. Across a suite of CNN and vision-transformer targets, LTA achieves strong transfer attack success while producing spatially coherent, predominantly low-frequency perturbations that differ qualitatively from pixel-space baselines and occupy a distinct point in the transfer-quality trade-off. Our results highlight pretrained generative latent spaces as an effective and structured domain for adversarial optimization, bridging robustness evaluation with modern generative priors.