Overview

Adversarial attacks study how deliberately chosen inputs, training data, model parameters, or system interactions can make AI systems fail or behave as intended by an attacker. Common approaches include gradient-based perturbations, black-box query and evolutionary search, generative or semantic changes, physical patches and sensor interference, and poisoning or backdoors. Work spans image, language, audio, graph, and time-series models as well as federated learning, recommenders, robotics, and AI agents, with evaluations on benchmarks and increasingly realistic deployment settings. A central tension is that attacks must be effective and stealthy under practical constraints, while defenses and benchmarks must keep pace with adaptive threats and distinguish digital robustness from real-world resilience.

Latest papers

CardsList

477 papers34 papers in the last four weeks, down 39% on the four weeks before. 0.3% of all new papers.

  1. Density Feedback Control for Transferability of Generative Sparse Adversarial Attacks

    Nov 18, 2026Dongsu Song, Jay Hoon JungAdversarial AttacksTransfer-Based Adversarial Attacks

  2. A Rank-One Bypass of Fixed Linear Erasure

    Nov 18, 2026Jai Kumar Sharma, Vanshaj KhattarAdversarial AttacksConcept Erasure

  3. NONSENSE: Non-Semantic Strings Expose Semanticity Gaps in Dense Retrieval

    Nov 17, 2026Ankit GuptaDense RetrievalIR Evaluation

  4. Wrong Input, Wrong Threshold: Re-evaluating Adversarial Facial Privacy

    Nov 16, 2026Tunahan Parlayıcı, Erchan Aptoula, Yücel SaygınAdversarial AttacksAdversarial Transferability

  5. STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies

    Nov 16, 2026Shenghao Xiong, Xiaolin ChangMultimodal RobustnessAdversarial Attacks

  6. Binarization as an Attack Surface in Weightless Neural Networks

    Nov 13, 2026Lucas Senos Coutinho, Matheus Vargas, Pedro Teixeira +5Adversarial AttacksAdversarial Robustness

  7. Structured Confidence Perturbation via Fisher Geometry for Adversarial Training

    Nov 10, 2026Chenlong Wei, Hanling Wang, Chong Zhang +3Adversarial TrainingAdversarial Robustness

  8. Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball

    Nov 10, 2026Andrew C. Cullen, Neil G. Marchant, Paul Montague +2Adversarial AttacksAdversarial Robustness

  9. Data Manipulation Attacks Against Machine Learning Integrated Cyber-Physical Systems

    Nov 8, 2026Soyon Choi, Scott Alfeld, Meiyi MaAdversarial AttacksCPS Security

  10. 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

  11. RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples

    Nov 5, 2026Chao Zhou, Shenghua He, Jiaxin Mo +2Adversarial AttacksBlack-Box Adversarial Attacks

  12. VIPA: View-Invariant Projector-Based Adversarial Attack

    Nov 5, 2026Jiyu Han, Qingyue Deng, Bingyao HuangAdversarial AttacksPhysical Adversarial Attacks

  13. JevBreak: Your Model, Their Decision

    Nov 2, 2026Nitin Aravind Birur, Divyanshu Kumar, Sahil Agarwal +1Adversarial AttacksAdversarial Text Attacks

  14. The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents

    Nov 2, 2026Geyuan Wang, Shunyu Liu, Siyuan Liang +2Adversarial AttacksAI Agent Security

  15. Black-Box Adversarial Example Attacks on Machine Learning based Election Systems

    Nov 1, 2026Subek Acharya, Syed Ayon, Khaleque Md Aashiq Kamal +3Adversarial AttacksBlack-Box Adversarial Attacks

  16. Step-Zero Attack: Agent Safety Before Observability

    Nov 1, 2026Tian Qin, Yuhang Jiang, Junzhe Chen +2AI Agent SecurityAI Agent Safety

  17. PASA-KV: Attacking Action-Facing Visual Routes in World Action Models

    Oct 29, 2026Zhongbo Wu, Jiakai Huang, Zheng Zhang +6Adversarial Attacks on World ModelsAdversarial Attacks

  18. FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models

    Oct 28, 2026Xiaogeng Liu, Xinyan Wang, Chaowei XiaoTyped Decision ModelsAdversarial Attacks

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

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

  20. A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks

    Oct 28, 2026Farid Mafi, Saber Jafarpour, Mohammad PiraniAdversarial AttacksGraph Neural Networks

  21. When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning

    Oct 27, 2026Vincess Dongmo, Astride Melvin Fokam NinyimGraph RobustnessAdversarial Attacks

  22. Quantifying and Prioritizing Stealthy Source-Manipulation Threats Against Multi-Source Anomaly Detectors

    Oct 27, 2026Indraveni Chebolu, Seema Panghal, Arnab Mallick +1Adversarial AttacksAnomaly Detection

  23. The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming

    Oct 26, 2026Mintong Kang, Stephen Rawls, Melissa Kazemi Rad +2LLM Red TeamingAutomated Red Teaming

  24. Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks

    Oct 26, 2026Raik Dankworth, Felix Mächtle, Thomas Eisenbarth +1Adversarial AttacksAdversarial Robustness