Adversarial Transferability

Ask about this topic

Overview

Adversarial transferability concerns whether a perturbation crafted using one model, often a surrogate, also fools an unseen model, making it central to black-box security testing. Researchers improve transfer with gradient-based attacks, surrogate ensembles, input transformations, and alignment of semantic, feature, or frequency cues; the same ideas are adapted to images, language, audio, physical settings, and structured tasks. Transfer tests also guide defenses such as adversarial training, input purification, and representation shaping. A key tension is that transfer depends on source–target compatibility: a method that helps against one kind of surrogate may hurt against another, while attack success alone does not capture imperceptibility or real-world risk.

Latest papers

CardsList

51 papers9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

  1. MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition

    Oct 22, 2026Wonjune Seo, Joonhyuk Baek, Yeseong Jung +1Adversarial AttacksTransfer-Based Adversarial Attacks

    Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea

  2. Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness

    Oct 19, 2026Leo Elmecker-Plakolm, Lukasz Szpruch, Avishek Joey Bose +1Adversarial RobustnessAdversarial Robustness of Language Models

    Imperial College London · The University of Edinburgh · The Alan Turing Institute +1

  3. Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices

    Oct 19, 2026Yuyang Zhang, Kangjie Chen, Yihui Jin +1Adversarial TransferabilityAdversarial Robustness

  4. Breaking Adversarial Transferability in Fine-Tuned Speech Recognition

    Oct 6, 2026Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3Adversarial TransferabilityAutomatic Speech Recognition

    Department of Computer Engineering Sharif University of Technology · Department of Computer Engineering University of Isfahan

  5. Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

    Oct 5, 2026Zexin Li, Ruili Yao, Yiming Zeng +1Adversarial AttacksTransfer-Based Adversarial Attacks

    Nanyang Technological University · University of California, Riverside · University of Connecticut +1

  6. Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs

    Oct 4, 2026Xiaojun Jia, Simeng Qin, Yiming Li +5Adversarial Attacks on VLMsAdversarial Attacks

    Nanyang Technological University, Singapore · Northeastern University, Shenyang, Liaoning, China · Chongqing University, Chongqing, China +2

  7. Pareto-Improving Adversarial Attacks with Primal-Dual Regularization

    Oct 3, 2026Yang Dai, Longfei Zhang, Wei Tao +3Adversarial AttacksTransfer-Based Adversarial Attacks

    Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China

  8. Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation

    Sep 30, 2026Linfeng Jiang, Steven McDonagh, Yuhang Chen +3Adversarial AttacksAdversarial Transferability

    University of Maryland, College Park · University of Edinburgh · WMG, University of Warwick +1

  9. Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework

    Sep 30, 2026Yaohua Liu, Yifan Guo, Jiaxin GaoAdversarial AttacksBilevel Optimization

    The University of Hong Kong Hong Kong, China · International School of Information Science & Engineering Dalian University of Technology, Dalian, China · The Hong Kong Polytechnic University Hong Kong, China

  10. AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

    Sep 26, 2026Gal Wertheizer, Rom Himelstein, Tomer Peretz +1Adversarial RobustnessAdversarial Robustness of Language Models

    Department of Computer Science, Technion — Israel Institute of Technology · Department of Data and Decision Sciences, Technion — Israel Institute of Technology

  11. AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders

    Sep 24, 2026Saim Rehman, Muhammad ShafiqueQuantization-Aware TrainingEEG Decoding

    eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE

  12. What Makes Adversarial Examples Transfer Across Deepfake Detectors?

    Sep 9, 2026Rafael M. Mamede, Pedro C. Neto, Ana F. SequeiraAdversarial RobustnessDeepfake Detection

    INESC TEC, Porto, Portugal · Faculty of Engineering, University of Porto (FEUP), Porto, Portugal · Unilabs, Porto, Portugal

  13. A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families

    Aug 27, 2026Yu Zhe, Yixin Tan, Junhao Wei +1Adversarial Attacks on LLMsLLM Jailbreak Attacks

    RIKEN AIP · Institute of Science Tokyo · Zhejiang University

  14. Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

    Aug 25, 2026Zuobin Xiong, Deval Mukherjee, Homook Cho +1Federated LearningTransfer-Based Adversarial Attacks

    Department of Computer Science, University of Nevada Las Vegas, Las Vegas, USA · Cyber Security Research Center at KAIST, Daejeon, South Korea · Department of Computer Science, Georgia State University, Atlanta, Georgia, USA

  15. On the Adversarial Robustness of Remote Sensing Semantic Change Detection

    Aug 15, 2026Weikang Yu, Yonghao Xu, Pedram GhamisiAdversarial RobustnessAdversarial Attacks

    Helmholtz Institute Freiberg for Resource Technology, Helmholtz-Zentrum Dresden-Rossendorf, 09599 Freiberg, Germany · Department of Electrical Engineering, Linköping University, 58183 Linköping, Sweden

  16. Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

    Aug 15, 2026Kaisheng Liang, Yiming Cao, Bin XiaoAdversarial AttacksTransfer-Based Adversarial Attacks

    Department of Computing, The Hong Kong Polytechnic University, Hong Kong

  17. Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

    Aug 12, 2026Yaohua Liu, Yifan Guo, Jiaxin GaoBilevel OptimizationTransfer-Based Adversarial Attacks

    The University of Hong Kong, Hong Kong SAR, China · International School of Information Science & Engineering, Dalian University of Technology, Dalian, China · The Hong Kong Polytechnic University, Hong Kong SAR, China

  18. IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

    Aug 9, 2026Yi Pan, Jun-Jie Huang, Tianrui Liu +3Adversarial AttacksTransfer-Based Adversarial Attacks

    College of Computer Science and Technology

  19. Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks

    Aug 5, 2026Tianyi Wang, Zhenghao Gao, Shengjie XuAdversarial AttacksTransfer-Based Adversarial Attacks

    Tongji University Shanghai, China · Huazhong University of Science and Technology · Wuhan LightRead Intelligent Technology Co., Ltd. Wuhan, China

  20. IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks

    Jul 29, 2026Mengqi He, Jing ZhangAdversarial AttacksTransfer-Based Adversarial Attacks

    School of Computing, College of Systems & Society · The Australian National University, Canberra, ACT, Australia

  21. Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing

    Jul 14, 2026Yataro Tamura, Brian Kenji Iwana, Jiseok LeeAdversarial AttacksOnline Handwriting Recognition

    Kyushu University, Fukuoka, Japan

  22. Transferable Attack against Face Swapping in an Extended Space

    Jun 24, 2026Mingzhi Lyu, Yi Huang, Jun Xie +3Adversarial AttacksAdversarial Perturbations

    Nanyang Technological University Singapore

  23. AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

    Jun 23, 2026Khanak KhandelwalAdversarial Prompt GenerationAdversarial Attacks on LLMs

    Indian Institute of Technology Jodhpur

  24. The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks

    Jun 21, 2026Yuhang Jiang, Xiaojing ChenNeural Network RobustnessAdversarial Robustness

    University of Trento · Anhui University

  25. Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

    Jun 9, 2026Lijia Yu, Jiuxin Cao, Yuchen Qiang +3Adversarial Attacks on VLMsTransfer-Based Adversarial Attacks

    School of Cyber Science and Engineering, Southeast University, China · Purple Mountain Laboratories, Nanjing, China

  26. SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack

    May 24, 2026Han Liu, Zhi Xu, Xiaotong Zhang +5Determinantal Point ProcessTransfer-Based Adversarial Attacks

    Dalian University of Technology Dalian, China · Peking University Beijing, China · Macao Polytechnic University Macao, China +1

  27. Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

    May 20, 2026Leitao Yuan, Qinghua Mao, Daizong Liu +5Adversarial Attacks on VLMsMultimodal Large Language Models

    Shanghai Artificial Intelligence Laboratory · Zhejiang University · Shanghai Jiao Tong University +3

  28. MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks

    May 18, 2026Hyo Seo Kim, Gang Luo, Can Chen +3Evolutionary OptimizationAdversarial Attacks

    Illinois Institute of Technology · University of North Carolina at Chapel Hill · Singapore Management University

  29. Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection

    May 18, 2026Yifan Liao, Yule Liu, Zhen Sun +5Audio Deepfake DetectionTransfer-Based Adversarial Attacks

    Wuhan University · The Hong Kong University of Science and Technology (Guangzhou)

  30. Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework

    May 18, 2026Ziyang Liu, Hongyuan Wang, Zijian Wang +4Transfer-Based Adversarial AttacksBlack-Box Adversarial Attacks

    Research Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, China · Zhengzhou Research Institute, Harbin Institute of Technology, Zhengzhou 450000, China