Adversarial Attacks

ICLR 2024arXiv:2307.14539

#2

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh

235

ECCV 2024arXiv:2310.11868

#3

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now

Yimeng Zhang, jinghan jia, Xin Chen et al.

176

ICML 2024arXiv:2309.00236

#4

Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Luke Bailey, Euan Ong, Stuart Russell et al.

adversarial imagesvision-language modelsbehavior matchingprompt matching+4

142

ICML 2025arXiv:2404.16873

#5

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Anselm Paulus, Arman Zharmagambetov, Chuan Guo et al.

adversarial promptingjailbreaking attackslarge language modelsprompt optimization+4

132

ICLR 2024arXiv:2310.13345

#6

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

Xilie Xu, Keyi Kong, Ning Liu et al.

131

CVPR 2024arXiv:2311.12075

#7

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Siyuan Liang, Mingli Zhu, Aishan Liu et al.

98

ICLR 2024arXiv:2303.09105

#8

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Huanran Chen, Yichi Zhang, Yinpeng Dong et al.

98

CVPR 2024arXiv:2308.10299

#9

Boosting Adversarial Transferability by Block Shuffle and Rotation

Kunyu Wang, he xuanran, Wenxuan Wang et al.

adversarial examplesadversarial transferabilityblack-box attacksinput transformation attacks+2

97

ICLR 2025arXiv:2406.12814

#10

Dissecting Adversarial Robustness of Multimodal LM Agents

Chen Wu, Rishi Shah, Jing Yu Koh et al.

adversarial robustnessmultimodal language modelsautonomous agentsagent robustness evaluation+4

81

ICLR 2024arXiv:2310.00076

#11

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei et al.

77

ICML 2024arXiv:2402.15570

#12

Fast Adversarial Attacks on Language Models In One GPU Minute

Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan et al.

adversarial attackslanguage model securityjailbreaking attacksprivacy attacks+4

72

ECCV 2024arXiv:2307.12499

#13

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

Xuelong Dai, Kaisheng Liang, Bin Xiao

59

CVPR 2024arXiv:2305.11618

#14

DAP: A Dynamic Adversarial Patch for Evading Person Detectors

Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif et al.

50

ICLR 2025arXiv:2405.18540

#15

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Seanie Lee, Minsu Kim, Lynn Cherif et al.

automated red-teaminglarge language modelssafety tuningreinforcement learning+4

46

CVPR 2024arXiv:2403.01849

#16

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

Lin Li, Haoyan Guan, Jianing Qiu et al.

adversarial robustnessvision-language modelsprompt tuningadversarial examples+3

45

ICLR 2024arXiv:2309.16952

#17

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Nils Lukas, Abdelrahman Ahmed, Lucas Fenaux et al.

41

CVPR 2024arXiv:2404.16452

#18

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

Lihua Jing, Rui Wang, Wenqi Ren et al.

adversarial patch attacksobject detectionpatch-agnostic defensesemantic independence+3

41

CVPR 2024arXiv:2405.09882

#19

DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection

Yuhao Sun, Lingyun Yu, Hongtao Xie et al.

adversarial makeup transferfacial privacy protectiondiffusion modelsmakeup removal module+4

38

AAAI 2024arXiv:2312.11285

#20

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

Decheng Liu, Xijun Wang, Chunlei Peng et al.

adversarial attacksface recognition modelslatent diffusion modelidentity-sensitive conditioning+4

37

CVPR 2024arXiv:2403.05247

#21

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

Tianrui Lou, Xiaojun Jia, Jindong Gu et al.

36

ICLR 2025arXiv:2406.12027

#22

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI

Robert Hönig, Javier Rando, Nicholas Carlini et al.

adversarial perturbationsstyle mimicryimage generation modelsartistic style protection+2

35

CVPR 2024arXiv:2404.09401

#23

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models

Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka

diffusion modelscopyright protectionadversarial exampleswatermark embedding+3

34

ICLR 2024arXiv:2402.11473

#24

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Jiawei Liang, Siyuan Liang, Aishan Liu et al.

33

CVPR 2024arXiv:2312.09558

#25

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

Yao Huang, Yinpeng Dong, Shouwei Ruan et al.

32

CVPR 2024arXiv:2405.14077

#26

Learning to Transform Dynamically for Better Adversarial Transferability

Rongyi Zhu, Zeliang Zhang, Susan Liang et al.

31

AAAI 2024arXiv:2402.03951

#27

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

Qinliang Lin, Cheng Luo, Zenghao Niu et al.

adversarial transferabilitycross model genus attackelastic deformationinput transformation+4

30

CVPR 2024arXiv:2211.08229

#28

Data Poisoning based Backdoor Attacks to Contrastive Learning

Jinghuai Zhang, Hongbin Liu, Jinyuan Jia et al.

30

ICCV 2025arXiv:2406.05491

#29

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Hao Fang, Jiawei Kong, Wenbo Yu et al.

30

ICML 2025arXiv:2410.17401

#30

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Chejian Xu, Mintong Kang, Jiawei Zhang et al.

29

ICLR 2025arXiv:2406.18382

#31

Adversarial Search Engine Optimization for Large Language Models

Fredrik Nestaas, Edoardo Debenedetti, Florian Tramer

28

CVPR 2024arXiv:2209.11964

#32

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

Zhengwei Fang, Rui Wang, Tao Huang et al.

27

ICML 2024arXiv:2402.15152

#33

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Yihao Zhang, Hangzhou He, Jingyu Zhu et al.

adversarial trainingsharpness-aware minimizationadversarial robustnessloss landscape+3

25

CVPR 2025arXiv:2412.03283

#34

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

Andreas Müller, Denis Lukovnikov, Jonas Thietke et al.

24

ICLR 2025arXiv:2506.16447

#35

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Biao Yi, Tiansheng Huang, Sishuo Chen et al.

backdoor unalignment attackslarge language modelsblack-box defensesafety alignment+4

23

ICML 2025arXiv:2406.14595

#36

Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement

Han Wu, Guanyan Ou, Weibin Wu et al.

Adversaries Can Misuse Combinations of Safe Models

Erik Jones, Anca Dragan, Jacob Steinhardt

19

CVPR 2024arXiv:2404.15081

#38

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

Jingyao Xu, Yuetong Lu, Yandong Li et al.

19

CVPR 2024arXiv:2403.10073

#39

Revisiting Adversarial Training Under Long-Tailed Distributions

Xinli Yue, Ningping Mou, Qian Wang et al.

ICLR 2024arXiv:2312.11954

#40

Adversarial AutoMixup

Huafeng Qin, Xin Jin, Yun Jiang et al.

NEURIPS 2025arXiv:2503.10635

#41

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

Zhaoyi Li, Xiaohan Zhao, Dong-Dong Wu et al.

AAAI 2025arXiv:2404.19460

#42

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor et al.

NEURIPS 2025arXiv:2505.21494

#43

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Xiaojun Jia, Sensen Gao, Simeng Qin et al.

adversarial attacksmultimodal large language modelsfeature alignmentoptimal transport+4

ICML 2025arXiv:2502.01633

#44

Adversarial Reasoning at Jailbreaking Time

Mahdi Sabbaghi, Paul Kassianik, George Pappas et al.

ICLR 2025arXiv:2502.03052

#45

Understanding and Enhancing the Transferability of Jailbreaking Attacks

Runqi Lin, Bo Han, Fengwang Li et al.

jailbreaking attackstransferability analysisintent perceptionadversarial sequences+3

AAAI 2024arXiv:2312.00198

#46

COMBAT: Alternated Training for Effective Clean-Label Backdoor Attacks

Tran Huynh, Dang Nguyen, Tung Pham et al.

Optimal Attack and Defense for Reinforcement Learning

Jeremy McMahan, Young Wu, Xiaojin Zhu et al.

17

AAAI 2024arXiv:2311.13091

#48

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

Yixin Liu, Kaidi Xu, Xun Chen et al.

unlearnable examplesdata poisoningadversarial trainingdefensive noise+4

17

CVPR 2025arXiv:2410.05346

#49

Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

Jiaming Zhang, Junhong Ye, Xingjun Ma et al.

ICML 2024arXiv:2402.15853

#50

RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation

Jiawei Zhou, Linye Lyu, Daojing He et al.

physical adversarial attackadversarial camouflage generationvehicle detectorsneural rendering+3

ICLR 2024arXiv:2308.12439

#51

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Tinghao Xie, Xiangyu Qi, Ping He et al.

ICLR 2024arXiv:2306.11035

#52

Adversarial Training Should Be Cast as a Non-Zero-Sum Game

Alex Robey, Fabian Latorre, George Pappas et al.

CVPR 2024arXiv:2306.15755

#53

Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving

Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli

AAAI 2025arXiv:2412.16958

#54

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

Yichen Wang, Yuxuan Chou, Ziqi Zhou et al.

ICML 2025arXiv:2112.07324

#55

Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples

Junhao Dong, Piotr Koniusz, Junxi Chen et al.

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

Chen Liu, Zhichao Huang, Mathieu Salzmann et al.

COLM 2025arXiv:2402.13532

#57

Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers

Quanyu Long, Yue Deng, Leilei Gan et al.

backdoor attackdense retrieval

AAAI 2024arXiv:2308.00319

#58

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

Ruikui Wang, Yuanfang Guo, Yunhong Wang

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

AAAI 2024arXiv:2312.12768

#60

Mutual-Modality Adversarial Attack with Semantic Perturbation

Jingwen Ye, Ruonan Yu, Songhua Liu et al.

ICLR 2024arXiv:2404.05311

#61

BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK

Quoc Viet Vo, Ehsan Abbasnejad, Damith Ranasinghe

CVPR 2025arXiv:2411.15720

#62

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks

Peng Xie, Yequan Bie, Jianda Mao et al.

vision-language modelsadversarial robustnesstransfer-based attacksmultimodal semantic correlation+3

ICLR 2024arXiv:2305.08840

#63

Attacking Perceptual Similarity Metrics

Abhijay Ghildyal, Feng Liu

ICLR 2025arXiv:2310.04687

#64

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Boyang Zheng, Chumeng Liang, Xiaoyu Wu

ICLR 2025arXiv:2503.00596

#65

BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge

Terry Tong, Fei Wang, Zhe Zhao et al.

ICLR 2024arXiv:2207.10170

#66

Illusory Attacks: Information-theoretic detectability matters in adversarial attacks

Tim Franzmeyer, Stephen McAleer, Joao F. Henriques et al.

12

AAAI 2024arXiv:2402.11083

#67

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

Ziyi Yin, Muchao Ye, Tianrong Zhang et al.

12

CVPR 2024arXiv:2403.11448

#68

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

Linyu Tang, Lei Zhang

12

ICLR 2024arXiv:2306.08386

#69

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Ziqiang Li, Hong Sun, Pengfei Xia et al.

11

ICML 2024arXiv:2405.19098

#70

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Shuyu Cheng, Yibo Miao, Yinpeng Dong et al.

black-box adversarial attacksbayesian optimizationadversarial transferabilitysurrogate model guidance+4

11

ICLR 2025arXiv:2502.01385

#71

Detecting Backdoor Samples in Contrastive Language Image Pretraining

Hanxun Huang, Sarah Erfani, Yige Li et al.

11

AAAI 2024arXiv:2312.08898

#72

ADBA: Approximation Decision Boundary Approach for Black-Box Adversarial Attacks

Feiyang Wang, Xingquan Zuo, Hai Huang et al.

Detection and Defense of Unlearnable Examples

Yifan Zhu, lijia Yu, Xiao-Shan Gao

ICML 2024arXiv:2209.00005

#74

Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

Zhiyuan He, Yijun Yang, Pin-Yu Chen et al.

adversarial example detectionself-supervised learningrepresentation similaritylabel consistency+4

ICML 2024arXiv:2404.00924

#75

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo et al.

adversarial patch attackspixel-wise regressionmonocular depth estimationoptical flow estimation+4

ICLR 2024arXiv:2310.10780

#76

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective

Ganghua Wang, Xun Xian, Ashish Kundu et al.

AAAI 2024arXiv:2210.14404

#77

Adversarial Purification with the Manifold Hypothesis

Zhaoyuan Yang, Zhiwei Xu, Jing Zhang et al.

AAAI 2024arXiv:2407.20653

#78

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon

CVPR 2025arXiv:2412.00114

#79

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Yue Cao, Yun Xing, Jie Zhang et al.

ICLR 2025arXiv:2410.08503

#80

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

Binghui Li, Yuanzhi Li

spiking neural networksadversarial attacksevent-based visiondynamic vision sensors+4

#81

Exploring Vulnerabilities in Spiking Neural Networks: Direct Adversarial Attacks on Raw Event Data

Yanmeng Yao, Xiaohan Zhao, Bin Gu

ECCV 2024

ICLR 2024arXiv:2310.17645

#82

PubDef: Defending Against Transfer Attacks From Public Models

Chawin Sitawarin, Jaewon Chang, David Huang et al.

ICLR 2024arXiv:2305.17342

#83

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

Xiangyu Liu, Souradip Chakraborty, Yanchao Sun et al.

adversarial policiesreinforcement learning agentsmulti-agent settingadversarial training+3

ICML 2025arXiv:2502.17254

#84

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

Simon Geisler, Tom Wollschläger, M. Hesham Abdalla et al.

ECCV 2024arXiv:2407.20657

#85

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon

ICML 2025arXiv:2503.01811

#86

AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses

Nicholas Carlini, Edoardo Debenedetti, Javier Rando et al.

AAAI 2025arXiv:2412.18770

#87

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models

Yu-An Liu, Ruqing Zhang, Jiafeng Guo et al.

ICLR 2024arXiv:2312.00157

#88

Universal Backdoor Attacks

Benjamin Schneider, Nils Lukas, Florian Kerschbaum

ICML 2025arXiv:2410.21471

#89

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models

Yaopei Zeng, Yuanpu Cao, Bochuan Cao et al.

AAAI 2025arXiv:2408.09469

#90

Enhancing Adversarial Transferability with Adversarial Weight Tuning

Jiahao Chen, Zhou Feng, Rui Zeng et al.

NEURIPS 2025arXiv:2506.07001

#91

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi et al.

AAAI 2025arXiv:2408.00352

#92

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Honglei Miao, Fan Ma, Ruijie Quan et al.

adversarial attackstext-to-motion generationlarge language modelsmotion generation security+3

ICCV 2025arXiv:2311.12084

#93

On the Robustness of Neural-Enhanced Video Streaming against Adversarial Attacks

Qihua Zhou, Jingcai Guo, Song Guo et al.

ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches

Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif et al.

ECCV 2024arXiv:2407.12292

#95

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

Youheng Sun, Shengming Yuan, Xuanhan Wang et al.

targeted adversarial attackadversarial example generationlatent representation injectionclass-agnostic attack+4

CVPR 2024arXiv:2404.01828

#96

Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay

Yuhang Zhou, Zhongyun Hua

adversarial attacksadversarial defensecatastrophic forgettingcontinual learning+4

AAAI 2025arXiv:2502.02438

#97

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

Yaling Shen, Zhixiong Zhuang, Kun Yuan et al.

COLM 2025arXiv:2504.06141

#98

Adversarial Training of Reward Models

Alexander Bukharin, Haifeng Qian, Shengyang Sun et al.

reward modelsrobustnessRLHF

ICLR 2025arXiv:2501.05783

#99

UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping

Yanjie Li, Kaisheng Liang, Bin Xiao

6

CVPR 2024arXiv:2312.07067

#100

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

Qian Li, Yuxiao Hu, Yinpeng Dong et al.

6