Adversarial Perturbations

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 77

All topics

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Jun 13, 2026Zhongye Liu, Yaopei Zeng, Yurui Chang +1Adversarial Attacks on VLMs Multimodal Robustness
Pennsylvania State University
ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space
Jun 11, 2026Pratyush ChaudhariMoral Reasoning in Language Models Language Model Safety Evaluation
Independent Researcher
Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
Jun 9, 2026Zi Yin, Peilin Chai, Siyuan Huang +1Adversarial Attacks Diffusion Policy
Tsinghua University · Independent Researcher · Johns Hopkins University +1
Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
Jun 8, 2026Lucas Görnhardt, Timo Bartels, Niklas Schwarz +1Adversarial Perturbations Object Detection
Technische Universität Braunschweig, Germany
Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
Jun 1, 2026Zhenyu Li, Tianyi ShangAdversarial Attacks Vector Quantization
Shandong Academy of Sciences · Fuzhou University
Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
May 29, 2026Ei Hmue Khine, Yao Li, Jiebao Sun +3Adversarial Attacks Adversarial Perturbations
School of Mathematics, Harbin Institute of Technology, Harbin 150001, China
Learning to Perturb Hidden Representations for Generalizable Deep Learning
May 28, 2026Hua LiNeural Network Generalization Adversarial Perturbations
Henan University
Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms
May 26, 2026Meghana Bhange, Ulrich Aïvodji, Elliot CreagerAlgorithmic Fairness Group Fairness
ÉTS Montréal, Mila · University of Waterloo, Vector Institute
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
May 26, 2026Xiang Fang, Wanlong Fang, Changshuo WangVLM Robustness Adversarial Attacks on VLMs
School of Software Engineering, Huazhong University of Science and Technology · Nanyang Technological University, Singapore · University College London
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
May 25, 2026Aditya SridharConcept Bottleneck Models Adversarial Attacks
Independent Researcher · Atlanta, GA, USA
Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
May 21, 2026Yilan Gao, Sida Huang, Hongyuan Zhang +1Model Extraction Attacks T2I Generation
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, P. R. China · Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China · The University of Hong Kong
CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
May 21, 2026Zhi Chen, Shehab Sarar Ahmed, Chenkai Wang +2Adversarial Training Adversarial Robustness
UIUC · UIUC & BUET
Personalized Face Privacy Protection From a Single Image
May 18, 2026Zachary Yahn, Fatih Ilhan, Tiansheng Huang +5Adversarial Attacks Adversarial Perturbations
Georgia Institute of Technology, Atlanta, Georgia, USA
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
May 15, 2026Ye Sun, Xin Wang, Jiaming Zhang +7Adversarial Attacks on VLMs Adversarial Perturbations
Fudan University · Nanyang Technological University · Tongji University
Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
May 13, 2026Lilin Zhang, Yimo Guo, Yue Li +2Adversarial Training Class-Imbalanced Learning
1Sichuan University · 2Dongfang Electric (Chengdu) Innovation Research Co., Ltd. · 3Southwest China Research Institute of Electronic Equipment
Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications
May 13, 2026Maxwell Standen, Junae Kim, Claudia SzaboAdversarial Attacks Adversarial Perturbations
The University of Adelaide · DST Group
A Mimetic Detector for Adversarial Image Perturbations
May 12, 2026Johnny CorbinoAdversarial Examples Adversarial Perturbations
Lawrence Berkeley National Laboratory · Berkeley, CA, USA
Disagreement-Regularized Importance Sampling for Adversarial Label Corruption
May 8, 2026Csongor Horváth, Ida-Maria Sintorn, Prashant SinghImportance Sampling Noisy-Label Learning
Department of Information Technology, Uppsala University, Uppsala, Sweden · Science for Life Laboratory, Uppsala University, Uppsala, Sweden
Adversarial Effects on Expressibility and Trainability in Distributed Variational Quantum Algorithms
May 5, 2026Abhishek Sadhu, Sharu Theresa JoseVariational Quantum Circuits Adversarial Perturbations
School of Computer Science, University of Birmingham · Edgbaston, Birmingham B15 2TT, United Kingdom
Real-Time Evaluation of Autonomous Systems under Adversarial Attacks
May 5, 2026Adithya Mohan, Xujun Xie, Venkatesh Thirugnana Sambandham +1Autonomous Driving Safety Evaluation Adversarial Robustness
AI Motion Institute, Technische Hochschule Ingolstadt, Germany
Distributed Learning with Adversarial Gradient Perturbations
May 5, 2026Nawapon Sangsiri, Yufei TaoDistributed Optimization Adversarial Perturbations
CUHK
Dual-branch Robust Unlearnable Examples
May 3, 2026Xianlong Wang, Hangtao Zhang, Wenbo Pan +4Adversarial Robustness Adversarial Examples
Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · University of Pennsylvania, Philadelphia, USA · Huazhong University of Science and Technology, Wuhan, China +2
Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
May 1, 2026Alexander Warnecke, Konrad RieckAdversarial Attacks Adversarial Examples
1BIFOLD & TU Berlin
Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models
May 1, 2026Hongrui Zheng, Liejun Wang, Zhiqing GuoAdversarial Attacks Adaptive Loss Weighting
School of Computer Science and Technology, Xinjiang University, Urumqi, China · Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi, China · Silk Road Multilingual Cognitive Computing International Cooperation Joint Laboratory, Xinjiang University, Urumqi, China
Low Rank Adaptation for Adversarial Perturbation
Apr 30, 2026Han Liu, Shanghao Shi, Yevgeniy Vorobeychik +2Adversarial Attacks Low-Rank Approximation
Washington University in St. Louis
Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?
Apr 26, 2026Ruiqing Sun, Xingshan Yao, Zhijing Wu +6Image Corruption Robustness Adversarial Robustness
Beijing Institute of Technology
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
Apr 25, 2026Jingyu Zhang, Jacky Wai Keung, Yan Xiao +3End-to-End Autonomous Driving Adversarial Attacks
Department of Computer Science, City University of Hong Kong, Hong Kong SAR · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
Apr 23, 2026Junyan Luo, Peipeng Yu, Jianwei Fei +4Adversarial Perturbations
Jinan University Guangzhou, China · University of Florence Florence, Italy · Dongguan University of Technology Dongguan, China
Adversarial Evasion in Non-Stationary Malware Detection: Minimizing Drift Signals through Similarity-Constrained Perturbations
Apr 23, 2026Pawan Acharya, Lan ZhangConcept Drift Adversarial Attacks
Northern Arizona University, Flagstaff, AZ, USA
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

Jun 13, 2026, cs.AIJ/K move · Enter open · S save

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades

Zhongye Liu, Yaopei Zeng, Yurui Chang, Lu Lin

Pennsylvania State University

Adversarial Attacks on VLMs Multimodal Robustness Adversarial Perturbations LLM Routing Multimodal Foundation Models

Open paper AskPDF arXiv

While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.

Momentum

Related topics

Latest papers 77