Adversarial Robustness

ECCV 2024arXiv:2403.09513

#2

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting

Yu Wang, Xiaogeng Liu, Yu Li et al.

105

ICLR 2024arXiv:2303.09105

#3

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Huanran Chen, Yichi Zhang, Yinpeng Dong et al.

98

CVPR 2024arXiv:2311.12075

#4

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

Siyuan Liang, Mingli Zhu, Aishan Liu et al.

98

CVPR 2024arXiv:2308.10299

#5

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

CVPR 2024arXiv:2312.03777

#6

On the Robustness of Large Multimodal Models Against Image Adversarial Attacks

Xuanming Cui, Alejandro Aparcedo, Young Kyun Jang et al.

adversarial attacksmultimodal modelsimage classificationvisual question answering+4

89

ICML 2024arXiv:2402.12336

#7

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Christian Schlarmann, Naman Singh, Francesco Croce et al.

adversarial attacksvision-language modelsclip modelrobust vision encoder+3

88

ICML 2024arXiv:2305.15241

#8

Robust Classification via a Single Diffusion Model

Huanran Chen, Yinpeng Dong, Zhengyi Wang et al.

diffusion modelsadversarial robustnessgenerative classifiersadversarial training+4

84

ICLR 2025arXiv:2406.12814

#9

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

#10

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

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

77

CVPR 2024arXiv:2305.11618

#11

DAP: A Dynamic Adversarial Patch for Evading Person Detectors

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

50

ICLR 2025arXiv:2405.18540

#12

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

ECCV 2024arXiv:2405.16341

#13

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

Changhoon Kim, Kyle Min, Yezhou Yang

46

CVPR 2024arXiv:2403.01849

#14

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 2025arXiv:2409.20089

#15

Robust LLM safeguarding via refusal feature adversarial training

Lei Yu, Virginie Do, Karen Hambardzumyan et al.

adversarial attacksrefusal feature ablationllm safeguardingresidual stream embedding+4

45

CVPR 2024arXiv:2404.16452

#16

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

ICLR 2024arXiv:2309.16952

#17

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Nils Lukas, Abdelrahman Ahmed, Lucas Fenaux et al.

41

ICML 2024arXiv:2404.09349

#18

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Brian Bartoldson, James Diffenderfer, Konstantinos Parasyris et al.

adversarial robustnessscaling lawsadversarial trainingimage classification+4

37

CVPR 2024arXiv:2403.05247

#19

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

#20

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:2401.04727

#21

Revisiting Adversarial Training at Scale

Zeyu Wang, Xianhang li, Hongru Zhu et al.

34

ICCV 2025arXiv:2411.13587

#22

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Taowen Wang, Cheng Han, James Liang et al.

33

CVPR 2024arXiv:2405.14077

#23

Learning to Transform Dynamically for Better Adversarial Transferability

Rongyi Zhu, Zeliang Zhang, Susan Liang et al.

31

ICML 2025arXiv:2410.17401

#24

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Chejian Xu, Mintong Kang, Jiawei Zhang et al.

29

CVPR 2024arXiv:2209.11964

#25

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

Zhengwei Fang, Rui Wang, Tao Huang et al.

27

ICLR 2024arXiv:2305.13991

#26

Expressive Losses for Verified Robustness via Convex Combinations

Alessandro De Palma, Rudy R Bunel, Krishnamurthy Dvijotham et al.

26

ICLR 2024arXiv:2404.19651

#27

Provably Robust Conformal Prediction with Improved Efficiency

Ge Yan, Yaniv Romano, Tsui-Wei Weng

25

AAAI 2025arXiv:2408.10682

#28

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

Hongbang Yuan, Zhuoran Jin, Pengfei Cao et al.

knowledge unlearningadversarial robustnesslarge language modelsadversarial attacks+2

25

ICML 2024arXiv:2402.15152

#29

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

ICLR 2024arXiv:2402.06244

#30

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

Zequn Yang, Yake Wei, Ce Liang et al.

24

ICLR 2024arXiv:2401.16352

#31

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

Guang Lin, Chao Li, Jianhai Zhang et al.

24

CVPR 2025arXiv:2411.16721

#32

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Han Wang, Gang Wang, Huan Zhang

23

ICLR 2024arXiv:2305.12872

#33

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game

Simin Li, Jun Guo, Jingqiao Xiu et al.

23

CVPR 2024arXiv:2301.13096

#34

Language-Driven Anchors for Zero-Shot Adversarial Robustness

Xiao Li, Wei Zhang, Yining Liu et al.

22

ICLR 2025arXiv:2410.19937

#35

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Tanqiu Jiang, Zian Wang, Jiacheng Liang et al.

22

ECCV 2024arXiv:2306.09124

#36

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks

Caixin Kang, Yinpeng Dong, Zhengyi Wang et al.

22

AAAI 2024arXiv:2310.06958

#37

Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement

Han Wu, Guanyan Ou, Weibin Wu et al.

Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks

Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin et al.

no-reference quality metricsadversarial attacksimage quality assessmentvideo quality assessment+3

19

NEURIPS 2025arXiv:2503.10635

#39

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.

18

CVPR 2024arXiv:2403.10073

#40

Revisiting Adversarial Training Under Long-Tailed Distributions

Xinli Yue, Ningping Mou, Qian Wang et al.

18

AAAI 2024arXiv:2312.00198

#41

Optimal Attack and Defense for Reinforcement Learning

Jeremy McMahan, Young Wu, Xiaojin Zhu et al.

17

AAAI 2024arXiv:2311.13091

#42

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:2504.11195

#43

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Lijun Sheng, Jian Liang, Zilei Wang et al.

adversarial robustnessvision-language modelstest-time tuningprompt tuning+4

CVPR 2025arXiv:2411.13136

#44

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models

Xin Wang, Kai Chen, Jiaming Zhang et al.

ICML 2024arXiv:2402.15853

#45

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:2306.11035

#46

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

Alex Robey, Fabian Latorre, George Pappas et al.

AAAI 2025arXiv:2412.16958

#47

Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples

Junhao Dong, Piotr Koniusz, Junxi Chen et al.

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

Yichen Wang, Yuxuan Chou, Ziqi Zhou et al.

ICLR 2024arXiv:2404.17947

#49

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

Yassine ABBAHADDOU, Sofiane ENNADIR, Johannes Lutzeyer et al.

ICML 2024arXiv:2405.20355

#50

Enhancing Adversarial Robustness in SNNs with Sparse Gradients

Yujia Liu, Tong Bu, Ding Jianhao et al.

adversarial robustnessspiking neural networksgradient sparsity regularizationadversarial attacks+3

AAAI 2024arXiv:2402.15959

#51

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks

Zhiying Jiang, Xingyuan Li, Jinyuan Liu et al.

image stitchingadversarial attacksfeature matchingadversarial training+2

CVPR 2024arXiv:2306.15755

#52

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

Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli

ICML 2025arXiv:2112.07324

#53

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

Chen Liu, Zhichao Huang, Mathieu Salzmann et al.

AAAI 2024arXiv:2312.10329

#54

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

Yuansan Liu, Ruqing Zhang, Mingkun Zhang et al.

adversarial trainingneural ranking modelsinformation retrievaladversarial robustness+4

AAAI 2024arXiv:2312.12768

#55

Mutual-Modality Adversarial Attack with Semantic Perturbation

Jingwen Ye, Ruonan Yu, Songhua Liu et al.

CVPR 2025arXiv:2408.16807

#56

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

Ruikui Wang, Yuanfang Guo, Yunhong Wang

STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models

Koushik Srivatsan, Fahad Shamshad, Muzammal Naseer et al.

ICLR 2025arXiv:2410.05694

#58

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

William June Suk Choi, Kyungmin Lee, Jongheon Jeong et al.

diffusion modelsimage manipulation defenseadversarial noisetext-guided editing+3

AAAI 2024arXiv:2308.00319

#59

Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks

Tong Wang, Yuan Yao, Feng Xu et al.

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

ICLR 2024arXiv:2404.05311

#61

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

Quoc Viet Vo, Ehsan Abbasnejad, Damith Ranasinghe

ICLR 2024arXiv:2305.08840

#62

Attacking Perceptual Similarity Metrics

Abhijay Ghildyal, Feng Liu

CVPR 2024arXiv:2403.17520

#63

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization

Xiangyu Yin, Wenjie Ruan

adversarial trainingfisher-rao normmodel complexityadversarial robustness+4

ICLR 2025arXiv:2310.04687

#64

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Boyang Zheng, Chumeng Liang, Xiaoyu Wu

CVPR 2025arXiv:2411.15720

#65

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

ICML 2024arXiv:2402.12780

#66

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates

Youssef Allouah, Sadegh Farhadkhani, Rachid Guerraoui et al.

federated learningbyzantine robustnessclient subsamplingrobust aggregation+4

CVPR 2024arXiv:2405.05588

#67

Model Inversion Robustness: Can Transfer Learning Help?

Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran et al.

ICML 2025arXiv:2501.07493

#68

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

Yangsibo Huang, Milad Nasr, Anastasios Angelopoulos et al.

ICML 2024arXiv:2310.12793

#69

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift

Lin Li, Yifei Wang, Chawin Sitawarin et al.

adversarial robustnessdistribution shiftout-of-distribution generalizationadversarial threat models+2

ICLR 2024arXiv:2207.10170

#70

Illusory Attacks: Information-theoretic detectability matters in adversarial attacks

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

AAAI 2025arXiv:2412.10713

#71

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors

Fengshuo Bai, Runze Liu, Yali Du et al.

adversarial attacksdeep reinforcement learningtargeted behavior attacksintention policy+4

ICLR 2024arXiv:2401.12532

#72

Generalizability of Adversarial Robustness Under Distribution Shifts

Bernard Ghanem, Kumail Alhamoud, Hasan Hammoud et al.

DAFA: Distance-Aware Fair Adversarial Training

Hyungyu Lee, Saehyung Lee, Hyemi Jang et al.

AAAI 2024arXiv:2305.16771

#74

Robust Nonparametric Regression under Poisoning Attack

Puning Zhao, Zhiguo Wan

robust nonparametric regressionpoisoning attackhuber loss minimizationkernel regression+3

AAAI 2024arXiv:2303.11611

#75

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation

Yuzheng Wang, Zhaoyu Chen, Dingkang Yang et al.

adversarial robustness distillationdata-free learningknowledge transferadversarial training+3

ECCV 2024arXiv:2306.12941

#76

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

Francesco Croce, Naman D. Singh, Matthias Hein

adversarial robustnesssemantic segmentationadversarial trainingrobustness evaluation+3

CVPR 2024arXiv:2403.11448

#77

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

Linyu Tang, Lei Zhang

CVPR 2024arXiv:2403.06668

#78

Towards Understanding and Improving Adversarial Robustness of Vision Transformers

Samyak Jain, Tanima Dutta

PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor

Jaewon Jung, Hongsun Jang, Jaeyong Song et al.

adversarial robustnessadversarial distillationadversarial examplesneural network security+2

ECCV 2024arXiv:2402.15429

#80

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation

Yi Zhang, Yun Tang, Wenjie Ruan et al.

ICML 2024arXiv:2405.19098

#81

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

ICML 2025arXiv:2407.18213

#82

Scaling Trends in Language Model Robustness

Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth et al.

CVPR 2024arXiv:2403.09101

#83

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement

Daiwei Yu, Zhuorong Li, Lina Wei et al.

ICML 2025arXiv:2502.01027

#84

Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees

Yannis Montreuil, Axel Carlier, Lai Xing Ng et al.

CVPR 2025arXiv:2503.03613

#85

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Songlong Xing, Zhengyu Zhao, Nicu Sebe

CVPR 2024arXiv:2405.05502

#86

Towards Accurate and Robust Architectures via Neural Architecture Search

Yuwei Ou, Yuqi Feng, Yanan Sun

AAAI 2024arXiv:2312.08898

#87

Detection and Defense of Unlearnable Examples

Yifan Zhu, lijia Yu, Xiao-Shan Gao

ICML 2024arXiv:2209.00005

#88

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

#89

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:2402.12673

#90

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Xiangyu Liu, Chenghao Deng, Yanchao Sun et al.

ICML 2024arXiv:2402.08991

#91

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

Chenlu Ye, Jiafan He, Quanquan Gu et al.

model-based reinforcement learningadversarial corruptionmaximum likelihood estimationtotal-variation information ratios+3

CVPR 2024arXiv:2402.17729

#92

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

Feiyang Wang, Xingquan Zuo, Hai Huang et al.

Towards Fairness-Aware Adversarial Learning

Yanghao Zhang, Tianle Zhang, Ronghui Mu et al.

adversarial robustnessknowledge distillationfeature distribution alignmentvariance gap reduction+4

#94

Adversarially Robust Distillation by Reducing the Student-Teacher Variance Gap

Junhao Dong, Piotr Koniusz, Junxi Chen et al.

ECCV 2024

ICLR 2024arXiv:2403.13134

#95

Robust NAS under adversarial training: benchmark, theory, and beyond

Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel et al.

ICLR 2025arXiv:2407.02551

#96

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

David Glukhov, Ziwen Han, I Shumailov et al.

information leakagedual-intent queriesinferential adversariessafety-utility trade-off+4

AAAI 2024arXiv:2210.14404

#97

Adversarial Purification with the Manifold Hypothesis

Zhaoyuan Yang, Zhiwei Xu, Jing Zhang et al.

AAAI 2024arXiv:2407.20653

#98

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

Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon

ICLR 2025arXiv:2410.08503

#99

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

Binghui Li, Yuanzhi Li

ICLR 2024arXiv:2311.01642

#100

Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

Aryaman Reddi, Maximilian Tölle, Jan Peters et al.