Backdoor Detection

Ask about this topic

Overview

Backdoor detection studies how to find models or inputs that behave normally in ordinary use but produce an attacker-chosen response when a hidden trigger is present. Methods inspect poisoned training data, model weights and activations, or behavior at inference time; common approaches include spectral analysis, activation clustering, trigger inversion, controlled input perturbations, and runtime monitoring. Work spans image and text classifiers, language and multimodal models, audio, graphs, and reinforcement-learning agents, with evaluations on benchmarks that vary attack types, trigger visibility, and access to training data or model internals. A central challenge is making detectors transfer to unseen attacks and model families while keeping false alarms low, since adaptive backdoors can evade signals that work in closed-world tests.

Latest papers

CardsList

53 papers8 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

  1. Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering

    Oct 24, 2026Soumita Chatterjee, Sudip Ghosh, Tamal Ghosh +2Backdoor DefenseBackdoor Detection

    Indian Institute of Engineering Science and Technology, Shibpur, India

  2. Beyond Static Cues: Unified Dynamic Detection of MLLM Backdoors via Dual-Flow Trajectory Analysis

    Oct 14, 2026Yinzhen Huang, Jiahe Xie, Yitong Sun +2Backdoor DetectionBackdoor Defense in LLMs

    Beihang University, Beijing, Beijing, China

  3. 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

  4. Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models

    Oct 12, 2026Zhifang Zhang, Qi Wei, Weitong Chen +5Backdoor DetectionMultimodal Large Language Models

    The University of Queensland · Nanyang Technological University · Adelaide University +2

  5. 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

  6. TMT: Runtime Backdoor Detection for Vision-Language-Action Policies on Unseen Tasks

    Oct 7, 2026Zirun Zhou, Jingfeng Zhang, HaoChuan Xu +4Backdoor Attacks on VLA ModelsBackdoor Detection

    The University of Auckland · Fudan University · Institute of Science Tokyo

  7. Weight Oracles: Reading Neural Network Weights with Language Models

    Oct 5, 2026Krishna Kabra, Constantin Venhoff, Christian Schroeder de WittLLM AuditingBackdoor Detection

    University of Oxford

  8. Security Properties of Neural Networks as Decision Problems

    Sep 30, 2026Adrian WurmNeural Network VerificationAdversarial Attacks

    BTU Cottbus–Senftenberg, Lehrstuhl Theoretische Informatik Platz der Deutschen Einheit 1, 03046 Cottbus, Germany

  9. 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

  10. Fusing Spectral Signatures and Activation Clustering for Backdoor Detection in Healthcare Imaging Models: Method, Implementation, and Evaluation

    Sep 13, 2026Suresh TamangBackdoor DetectionMedical Imaging

    Graduate Researcher, Artificial Intelligence, University of the Cumberlands

  11. SpecGuard: Inference-Time Backdoor Detection For Free

    Sep 10, 2026Rui Wen, Ahmed Salem, Andrew Paverd +2Backdoor DetectionBackdoor Defense in LLMs

    Institute of Science Tokyo · Microsoft Security Response Center · Microsoft Azure +1

  12. Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

    Sep 2, 2026Ahmed Abdelnaby, Mohamed ElmahallawyBackdoor DetectionBackdoor Defense

    School of Engineering and Applied Sciences, Washington State University, Richland, WA 99354, USA

  13. Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift

    Aug 19, 2026Longtian Wang, Zhengyu Zhao, Chenhao Lin +5Backdoor DetectionBackdoor Attacks

    Xi’an Jiaotong University, Xi’an, China · Singapore Management University, Singapore

  14. Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles

    Aug 17, 2026Anik JhaEnsemble DiversityEnsemble Learning

    Independent Researcher

  15. When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers

    Aug 12, 2026Yang Liu, Ran ZouLanguage Model AuditingLLM Backdoor Attacks

    Department of Statistics and Operations Research, University of North Carolina at Chapel Hill · Department of Statistics, University of California, Irvine

  16. LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

    Aug 7, 2026Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1LLM Backdoor AttacksBackdoor Detection

    Michigan Technological University · Miami University · Lehigh University

  17. When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning

    Aug 4, 2026Yiming Chen, Kemou Li, Haiwei Wu +1Backdoor DetectionMultimodal Contrastive Learning

    State Key Laboratory of Internet of Things for Smart City, University of Macau · School of Computer Science and Engineering, University of Electronic Science and Technology of China

  18. Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures

    Aug 3, 2026Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni +3Backdoor DetectionParameter-Efficient Fine-Tuning

    University of Pisa

  19. Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

    Jul 30, 2026Roberto Riaño, Gorka Abad, Stjepan Picek +1Backdoor AttacksBackdoor Detection

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

  20. ToxScreen: Detecting Whether an LLM Has Been Poisoned

    Jul 29, 2026Anthony Hughes, Nicole Xing, Collin Francel +2LLM Backdoor AttacksBackdoor Detection

    University of Sheffield · Yale University · University of Alabama +2

  21. Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

    Jul 27, 2026Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1Multi-Agent LLM SystemsLLM Backdoor Attacks

    Illinois Institute of Technology Chicago, Illinois, USA

  22. SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models

    Jul 17, 2026Jinwen Xin, Xixiang LvBackdoor DetectionAutomatic Speech Recognition

    School of Cyber Engineering Xidian University Xi’an, China

  23. When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

    Jul 13, 2026Yibo Hu, Ren WangBackdoor AttacksBackdoor Detection

    Illinois Institute of Technology

  24. Detecting Ladder Logic Bombs in IEC 61131-3 PLC Programs using ESBMC-PLC+: A Formal Verification Approach with Trigger Synthesis

    Jul 9, 2026Pierre Dantas, Lucas Cordeiro, Waldir JuniorIndustrial Control System SecurityCybersecurity

    Electrical Engineering Federal University of Amazonas (UFAM) Manaus, AM, Brazil

  25. Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

    Jul 9, 2026Anjun Gao, Yueyang Quan, Zhuqing Liu +1LLM Backdoor AttacksBackdoor Detection

    University of Louisville · University of North Texas

  26. ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN

    Jul 7, 2026Md Raihan Uddin, Fatemeh Lotfi, Tolunay Seyfi +1Adversarial AttacksBackdoor Detection

    Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA

  27. Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

    Jul 7, 2026Qi Zhao, Christian WressneggerBackdoor AttacksBackdoor Detection

    KASTEL Security Research Labs · Karlsruhe Institute of Technology (KIT)

  28. Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages

    Jul 6, 2026Lucas PintoBackdoor DetectionAI Agent Monitoring

    Independent Researcher

  29. CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs

    Jun 30, 2026Zhengxing Li, David J. Miller, Guangmingmei Yang +1LLM Backdoor AttacksBackdoor Detection

    Electrical Engineering Dept Penn State University University Park, PA 16802 · Anomalee Inc. · Computer Science & Engineering Dept Penn State University University Park, PA 16802 +1

  30. Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

    May 28, 2026Travis LelleLLM Backdoor AttacksBackdoor Detection