Backdoor Attacks

Follow this topic Ask about this topic

Recent momentum

-57%

12 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

5 new papers

A weekly snapshot of new work published in Backdoor Attacks.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Backdoor Attacks.

Period ending 2026-09-07

3 new papers

A weekly snapshot of new work published in Backdoor Attacks.

157 papers

Latest in Backdoor Attacks

Browse all topics →

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel
Jun 29, 2026Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1Semantic Communications Backdoor Attacks
CouCE: A Unified Causal Framework for Debiased Deep Metric Learning
Jun 29, 2026Xin Yuan, Zhenyang Niu, Meiqi Wan +3Counterfactual Learning Causal Representation Learning
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
Jun 29, 2026Maxime Riché, Daniel Tan, Vili Kohonen +1Misalignment Indirect Prompt Injection
Fuzzing Large Language Models to Elicit Hidden Behaviours
Jun 28, 2026Mohammed Abu Baker, Lakshmi Babu-SaheerFuzzing Backdoor Attacks
The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training
Jun 28, 2026Tuo Chen, Minjing Dong, Benlei Cui +2Backdoor Attacks Encoders
A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization
Jun 27, 2026Guangmingmei Yang, David J. Miller, George KesidisTransformation-Based Attacks Backdoor Attacks
TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models
Jun 24, 2026William Aiken, Paula Branco, Guy-Vincent Jourdan +1Backdoor Attacks Adversarial Examples
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Jun 24, 2026Kavindu Herath, Joshua C. Zhao, Saurabh BagchiBackdoor Attacks Federated Learning
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
Jun 22, 2026Vu Tuan Truong, Long Bao LeBackdoor Attacks Higher Attack Success Rates
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
Jun 22, 2026Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan +2Molecular Graphs Backdoor Attacks
CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition
Jun 22, 2026Toby Briston, Illya Kosyk, Kuniyih SHuman Activity Recognition Backdoor Attacks
SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors
Jun 21, 2026Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab +2Backdoor Attacks Federated Learning
Fusing Backdoors, Machine Learning, and Optimization for Large-Scale Parametric Mixed-Integer Programs
Jun 19, 2026El Mehdi Er Raqabi, Pascal Van HentenryckMixed-Integer Programming Machine Learning
BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving
Jun 19, 2026Zhe Shuai, Xiaopeng Xie, Yikun ZengAutonomous Driving Video World Models
Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning
Jun 19, 2026Yongbin Huang, Xihao Xie, Jia ZhangBackdoor Attacks Poisoning
Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection
Jun 18, 2026Ziba Parsons, Ang Li3D Object Detection Light Detection And Ranging
FloatDoor: Platform-Triggered Backdoors in LLMs
Jun 17, 2026Nils Loose, Jonas Sander, Felix Mächtle +1Language Model Evasion Attacks Large Language Model Serving
Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning
Jun 15, 2026Xiaolin Li, Ning Wang, Ninghui Li +1Differential Privacy Federated Learning
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
Jun 15, 2026David Huang, Jaewon Chang, Avidan Shah +2Data Poisoning Backdoor Attacks
InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset
Jun 14, 2026Zhenyu YuBackdoor Attacks Training-Free Inference Framework
Continual Backdoor Training in IoT/CPS
Jun 12, 2026Oxana Salish, Kuniyilh SInternet Of Thing Backdoor Attacks
Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning
Jun 12, 2026Zhenqian Zhu, Yamin Hu, Yujiang Liu +5Backdoor Attacks Adversarial Examples
PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent
Jun 11, 2026Junfeng Guo Heng HuangBackdoor Attacks Test Time
From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
Jun 10, 2026Zhenqian Zhu, Yamin Hu, Yiya Diao +3Continual Model Merging Backdoor Attacks
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
Jun 10, 2026Kazuki Iwahana, Masaru Matsubayashi, Takuma Koyama +3Backdoor Attacks Language Model Evasion Attacks
Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips
Jun 8, 2026Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic +2Federated Learning Backdoor Attacks
Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs
Jun 6, 2026Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal +4Backdoor Attacks Language Model Evasion Attacks
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Jun 2, 2026Lisa Bouger, Théo Lasnier, Philippe Loubet Moundi +2Backdoor Attacks Large Language Model Unlearning
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Jun 2, 2026Anjun Gao, Yueyang Quan, Yufei Xia +2Large Language Model Jailbreaks Adversarial Jailbreaks
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Jun 1, 2026Ivan Sabolić, Marin Oršić, Josip Šarić +1Large Vision Language Models Backdoor Attacks
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
May 29, 2026Ziqing Yang, Rui Wen, Xinlei He +3Backdoor Attacks Model-Agnostic Defense
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
May 28, 2026Travis LelleBackdoor Attacks Language Model Evasion Attacks
Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation
May 27, 2026Jianwei Li, Jung-Eun KimBackdoor Attacks Trigger
Density-aware Sample-specific Attack
May 27, 2026Qiyuan Wang, Yao Li, Raymond K. W. WongBackdoor Attacks Model-Agnostic Defense
Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems
May 26, 2026Abile Jean, Kuniyilh SCyber-Physical System Backdoor Attacks
Conceptual Steganography
May 26, 2026Zhejian Zhou, Jonathan MayLarge Language Model Reasoning Steganography
When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
May 21, 2026Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating +1Backdoor Attacks Trigger
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
May 21, 2026Quang Duc Nguyen, Siyuan Liang, Yiming Li +2Backdoor Attacks Entanglement
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
May 20, 2026Aman Saxena, Jan Schuchardt, Yan Scholten +1Differential Privacy Backdoor Attacks
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
May 20, 2026Yifei Wang, Tianlin Li, Xiaohan Zhang +3Language Model Evasion Attacks Backdoor Attacks
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
May 19, 2026Sayan Biswas, Antoine Boutet, Davide Frey +7Backdoor Attacks Detection Framework
Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
May 19, 2026Kai Wang, Jiale Zhang, Chengcheng Zhu +2Text-To-Image Diffusion Models Backdoor Attacks
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
May 19, 2026Zeyao Liu, Zhendong Zhao, Xiaojun Chen +3Backdoor Attacks Generative Adversarial Network
Backdooring Masked Diffusion Language Models
May 19, 2026Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou +3Masked Diffusion Language Models Backdoor Attacks
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
May 19, 2026Tobias Braun, Jonas Henry Grebe, Hossein Shakibania +2Adversarial Examples Backdoor Attacks
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
May 18, 2026John T. Halloran, Noopur S. BhattLanguage Model Evasion Attacks Data Poisoning
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
May 18, 2026Kaiwen Luo, Zhenhong Zhou, Leo Wang +31Large Audio Language Models Large Language Model Safety
Language-Switching Triggers Take a Latent Detour Through Language Models
May 18, 2026Francis Kulumba, Wissam Antoun, Théo Lasnier +2Backdoor Attacks Trigger
Can Quantum Federated Learning Withstand Circuit-Level Backdoors?
May 18, 2026Aakar Mathur, Mohammed Ruknuddin, Ashish GuptaVariational Quantum Circuits Federated Learning
Fast and Lightweight Backdoor Detection via Head Random Probing
May 17, 2026Yinbo Yu, Xueyu Yin, Jing Fang +4Backdoor Attacks Detection Framework
Lightweight and Fast Backdoor Model Detection
May 17, 2026Yinbo Yu, Jing Fang, Xuewen Zhang +4Backdoor Attacks Attack Detection
Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
May 16, 2026Mengting Pan, Fan Li, Chen Chen +1Backdoor Attacks Graph Neural Networks
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
May 15, 2026Xuanyu Ge, Zhongqi Wang, Jie Zhang +2Backdoor Attacks Large Vision Language Models
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
May 14, 2026Rui Wen, Mark Russinovich, Andrew Paverd +2Backdoor Attacks Language Model Evasion Attacks
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
May 14, 2026Oubo Ma, Ruixiao Lin, Yang Dai +4Backdoor Attacks Deep Reinforcement Learning
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
May 13, 2026Marte Eggen, Eirik Reiestad, Kristian Gjøsteen +1Backdoor Attacks Neural Network
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
May 13, 2026Ziyang You, Liling Zheng, Xiaoke Yang +1Backdoor Attacks Random
Clausal Deletion Backdoors for QBF: a Parameterized Complexity Approach
May 12, 2026Leif Eriksson, Victor Lagerkvist, Sebastian Ordyniak +3Satisfiability Computable
BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
May 12, 2026Xiaoting Lyu, Yufei Han, Hangwei Qian +6Backdoor Attacks Large Language Model Backbones
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
May 12, 2026Ziyu Liu, Tao Li, Tianjie Ni +5Language Model Evasion Attacks Backdoor Attacks

Jun 29, 2026 · cs.NIJ/K move · Enter open · S save

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener, Sennur Ulukus

Nexcepta, Gaithersburg, MD, USA · The Ohio State University, Columbus, OH, USA · University of Maryland, College Park, MD, USA

Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless channels. The adoption of SemCom in shared-access wireless networks introduces new vulnerabilities for multi-user semantic inference. This paper considers a SemCom system for two transmitters communicating with a common receiver over a multiple access channel. Each transmitter maps source information into latent semantic representations, while the receiver jointly reconstructs and classifies the semantic information for both transmitters. A selective over-the-air backdoor (Trojan) attack is presented in which an adversary transmits a low-power trigger waveform over the air and injects it into the shared received signal during training. By transmitting the trigger again during testing, this stealthy, low-power attack selectively manipulates the semantic inference for one transmitter while minimally affecting the inference of the other transmitter. To mitigate this vulnerability, a trigger-aware defense mechanism is developed to preserve correct semantic labels under trigger-contaminated wireless observations. The results demonstrate both the vulnerability of shared-access SemCom systems to selective over-the-air backdoor attacks and the effectiveness of trigger-aware robust training for semantic protection.

Semantic Communications Backdoor Attacks Transformation-Based Attacks Wireless Networks

Open paper Ask about it PDF