Transfer-Based Adversarial Attacks

Overview

Transfer-based adversarial attacks study how to craft adversarial inputs using a surrogate model that also fool unseen target models, often when those targets are black boxes. Common approaches use gradient-based optimization, surrogate ensembles, input transformations, or alignment of semantic and intermediate features to reduce overfitting to one model. The methods span image classifiers, object detectors, speech systems, and vision-language models, with work also exploring physical patches and constraints on perceptual quality. A central challenge is that gains depend on how well the surrogate matches the target, so transfer success can vary across architectures and settings, making careful source–target evaluation essential.

Latest papers

CardsList

90 papers8 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

  1. Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer

    Nov 11, 2026Zhisheng Zhang, Yifan Mi, Yixuan Zhou +6Transfer-Based Adversarial AttacksAdversarial Robustness of ASR

  2. Query-Only Prompt-Agnostic Attacks on Visual In-Context Learning

    Nov 8, 2026Xiao Hu, Muhammad Ibrahim, Hao Wen +3Black-Box Adversarial AttacksIn-Context Learning

  3. Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception

    Nov 6, 2026Hongwei Lin, Xun Huang, Chenglu Wen +1Adversarial AttacksTransfer-Based Adversarial Attacks

  4. FGSM Attack Transferability from Simulation to Quantum Hardware in Network Intrusion Detection

    Oct 28, 2026Zeeshan Ajmal, Kimmo Halunen, Marc Maußner +2Label-Flipping AttacksAdversarial Attacks

  5. Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs

    Oct 27, 2026Ahmed Abdelnaby, Mohamed ElmahallawyAdversarial Attacks on VLMsTransfer-Based Adversarial Attacks

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

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

  7. Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive Radars

    Oct 20, 2026Tongrun Xing, Yongjun Dai, Xuan Liao +4Adversarial AttacksPhysical Adversarial Attacks

  8. Tricking Synthetic Image Detectors with Amortized Generative Attacks

    Oct 18, 2026Mohamed Awad, Khaled Elhady, Yasser Rohaim +2Adversarial Attacks on AI-Generated Image DetectorsAdversarial Attacks

  9. TAPDreamer: Transferable Adversarial Patches for World Action Models

    Oct 5, 2026Xuanyu Lu, Fengqing Jiang, Kaiyuan Zheng +8Adversarial Patch AttacksAdversarial Attacks

  10. Reward Stealing Attack on Large Language Models

    Oct 5, 2026Jiaming Qian, Pengyang Zhou, Jiahe Xu +1LLM AlignmentModel Extraction Attacks

  11. Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

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

  12. 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

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

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

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

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

  15. 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 VLMsAdversarial Attacks on LLMs

  16. 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

  17. What Makes Adversarial Examples Transfer Across Deepfake Detectors?

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

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

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

  19. Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

    Aug 23, 2026Wenyun Li, Guiping Cao, Xiangyuan Lan +1Adversarial Attacks on Unified Multimodal ModelsMultimodal Jailbreak Attacks

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

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

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

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

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

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

  23. Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

    Aug 7, 2026Elena Dumitrescu, Gert Lek, Lydia Y. Chen +1Adversarial Attacks on LLMsLLM Safety Alignment

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

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

  25. Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

    Aug 2, 2026Wanguang Li, Zhaoxin Wang, Handing WangAdversarial Prompt GenerationT2I Generation

  26. DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

    Jul 31, 2026Omid Ahmadieh, Nima KarimianAdversarial AttacksTransfer-Based Adversarial Attacks