Backdoor Attacks

Ask about this topic

Overview

Backdoor attacks study how hidden behaviors can be implanted in machine-learning systems and activated by a trigger, even when performance on ordinary inputs appears normal. Attackers use poisoned training data, malicious model updates, or compromised components; triggers range from image patches and text styles to graph structures, timing patterns, and an agent’s internal state. Research spans image and speech classifiers, language and diffusion models, federated learning, reinforcement learning, and agent systems, with defenses including data filtering, model inspection, fine-tuning, and runtime monitoring. A central challenge is that defenses can miss unfamiliar or deployment-specific triggers, while stronger mitigation may reduce useful performance and some backdoors may be difficult to detect even with access to model parameters.

Latest papers

CardsList

135 papers16 papers in the last four weeks, up 23% on the four weeks before. 0.1% of all new papers.

  1. Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring

    Oct 23, 2026Yu-Yu Lee, Ming-Feng Tsai, Tomohiro Morikawa +1Backdoor AttacksLLM Backdoor Attacks

    Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan · Department of Computer Science and Engineering and the Security Research Center, National Sun Yat-sen University, Kaohsiung 804, Taiwan · University of Hyogo, Kobe, Japan +1

  2. Poisoning-Based Backdoors Are Not Cryptographic

    Oct 20, 2026Masahiro KanekoBackdoor AttacksLLM Backdoor Attacks

    MBZUAI

  3. You Are the Trigger: Speaker-Activated Backdoors

    Oct 19, 2026Nataša Krčo, Euodia Dodd, Peter Romov +1Backdoor AttacksAutomatic Speech Recognition

    Imperial College London

  4. Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents

    Oct 17, 2026Wonjun Lee, Vaidehi Patil, Zaid Khan +4AI Agent SafetyBackdoor Defense in LLMs

    UNC Chapel Hill · Kyung Hee University

  5. Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse

    Oct 15, 2026Junhoo Lee, Baekseung Kim, Seungyeon Kim +1Backdoor AttacksBackdoor Attacks on VLMs

    Seoul National University · Now at KAIST.

  6. Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness

    Oct 14, 2026Behrad Tajalli, Henk Berendsen, Xiaoyun Xu +1Backdoor Attacks

    Radboud University, Nijmegen, The Netherlands · University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia

  7. Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection

    Oct 14, 2026Florian Spelter, Johannes F. Loevenich, Tobias Hürten +4Backdoor AttacksData Poisoning Attacks

    CortAIx Labs, Thales Deutschland, Ditzingen, Germany · Grey Solutions, Düsseldorf, Germany · Department of Mathematics/Computer Science, University of Osnabrück, Osnabrück, Germany +2

  8. EvolvAttack: Backdooring self Evolving VLM Agents

    Oct 11, 2026Chuan Zou, Yang Xiang, Zexin Li +2Backdoor AttacksBackdoor Attacks on VLMs

    University of Pennsylvania · Brown University · Nanyang Technological University +2

  9. AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes

    Oct 10, 2026Zhuoxuan Zhang, Jinhao Duan, Xinyu Zhao +7Data Poisoning AttacksGenerative Recommendation

    University of North Carolina at Chapel Hill · University of Notre Dame · Meta

  10. AI Models Can Provably Hide Arbitrary Capabilities

    Oct 9, 2026Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas +1Backdoor Attacks

    Contramont Research · University of Oxford · ACS Research

  11. Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors

    Oct 9, 2026Arnab Dey, Mohammad Mahfuzul IslamBackdoor DetectionBackdoor Attacks

    Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka, Bangladesh

  12. Backdooring Acoustic Foundation Models for Physically Realizable Triggers

    Oct 7, 2026Zebin Yun, Eyal Ronen, Mahmood SharifBackdoor AttacksAdversarial Attacks

    Tel Aviv University, Tel Aviv, Israel

  13. The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

    Oct 6, 2026Yibo Zhang, Tianrong Guan, Liang Lin +3LLM Backdoor AttacksBackdoor Attacks

    Queen Mary University of London, UK · Squirrel AI Learning, USA

  14. Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System

    Oct 5, 2026Keegan Wang, Anantika MannbyLLM Backdoor AttacksAI Agent Auditing

    Carnegie Mellon University Prosaic Intelligence · University of Southern California Prosaic Intelligence

  15. BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided Triggers

    Sep 30, 2026Zhihang Wu, Zhongqi Wang, Jie Zhang +3Action-Conditioned Video GenerationBackdoor Attacks

    Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese of Sciences, Beijing, China

  16. Why Backdooring Neural Networks is so Easy?

    Sep 28, 2026Issam Seddik, Mohamed El Amine SeddikBackdoor Attacks

    Université Paris-Saclay, CEA LIST Palaiseau, France · AI Research Center, Technology Innovation Institute (TII) Abu Dhabi, UAE

  17. Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers

    Sep 26, 2026Beining Xu, Peichun Hua, Yunming XiaoBackdoor AttacksRAG Security

    Shenzhen MSU-BIT University · The Chinese University of Hong Kong, Shenzhen

  18. ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

    Sep 23, 2026Li Zeng, Mingcheng Duan, Longfei Fan +5Backdoor AttacksBackdoor Defense

    School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China · School of Computer Science, Xiangtan University, Xiangtan 411105, China · School of Software, Yunnan University, Kunming 650500, China +3

  19. LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models

    Sep 22, 2026Jin Wei, Rundong Li, Ruihao Yang +10Adversarial Attacks on Diffusion ModelsBackdoor Attacks

    School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China · School of Computing, Xi’an Jiaotong-Liverpool University +2

  20. Implementing a White-Box Undetectable Backdoor for Random Fourier Features

    Sep 14, 2026Michael Collins, Jada Cumberland, Brianne Dunn +3Adversarial AttacksBackdoor Attacks

    Laboratory for Advanced Cybersecurity Research Laurel, MD 20707 · School of Cybersecurity Old Dominion University Norfolk, VA 23259 · Old Dominion University Norfolk, VA 23259 +1

  21. When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control

    Sep 14, 2026Roberto Riaño, Gorka Abad, Stjepan Picek +1Backdoor AttacksLatent World Models

    Radboud University, The Netherlands · IKERLAN Technology Research Centre, Spain · University of Bergen, Norway +1

  22. Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

    Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia Smith +2LLM Backdoor AttacksBackdoor Attacks

    Carnegie Mellon University · Anthropic

  23. Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

    Sep 10, 2026Toshif Khan, Muhammad AbusaqerAdversarial AttacksBackdoor Attacks

    Minot State University

  24. TrojanWorld: Backdooring World-Model Agents via Imagination Steering

    Sep 7, 2026Wenkai Huang, Siyuan Liang, Gaolei Li +4Backdoor AttacksAdversarial Attacks on World Models

    Shanghai Jiao Tong University · Nanyang Technological University

  25. FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models

    Sep 7, 2026Yasir Arafat Prodhan, Sadad Hasan, Mohammed Imamul Hassan BhuiyanBackdoor AttacksBackdoor Attacks on VLMs

  26. CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning

    Sep 2, 2026Chao Feng, Burkhard StillerBackdoor AttacksBackdoor Attacks in Federated Learning

    Communication Systems Group, Department of Informatics University of Zurich, Switzerland

  27. GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition

    Sep 2, 2026Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz +4Backdoor AttacksAutomatic Speech Recognition

    Sharif University of Technology · Isfahan University

  28. Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems

    Sep 2, 2026Doniyorkhon Obidov, Shivayogi Akki, Tan Chen +1Backdoor AttacksLLM Backdoor Attacks

    Electrical and Computer Engineering Department, Michigan Technological University, Houghton, MI 49931, USA

  29. Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers

    Aug 31, 2026Yunjie Zhou, Yuheng Huang, Diqun YanBackdoor AttacksSpeech Enhancement

    Faculty of Electrical Engineering and Computer Science, Ningbo University, China · College of Artificial Intelligence, Ningbo University of Finance and Economics, China

  30. FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation

    Aug 27, 2026Zhiyang Chen, Changchun Yin, Huiqin Yang +1Backdoor AttacksAdversarial Attacks

    College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China