Backdoor Attacks

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, down 14% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 87

All topics

Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
May 19, 2026Kai Wang, Jiale Zhang, Chengcheng Zhu +2Backdoor Attacks Diffusion Model Fine-Tuning
Yangzhou University · Nanjing University · Chongqing University +1
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
May 19, 2026Tobias Braun, Jonas Henry Grebe, Hossein Shakibania +2Unified Multimodal Models Backdoor Attacks
TU Darmstadt & hessian.AI, Germany
Lightweight and Fast Backdoor Model Detection
May 17, 2026Yinbo Yu, Jing Fang, Xuewen Zhang +4Backdoor Attacks Backdoor Detection
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, 210016, China · Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, Guangdong, 518057, China · School of Software, Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P.R. China +2
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
May 14, 2026Rui Wen, Mark Russinovich, Andrew Paverd +2LLM Backdoor Attacks Backdoor Attacks
Institute of Science Tokyo · 2Microsoft Azure · 3Microsoft Security Response Center
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
May 14, 2026Oubo Ma, Ruixiao Lin, Yang Dai +4Reinforcement Learning Backdoor Attacks
1Zhejiang University · 2National University of Defense Technol · 3Xi’an Jiaotong University
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
May 13, 2026Marte Eggen, Eirik Reiestad, Kristian Gjøsteen +1Backdoor Attacks Backdoor Detection
Department of Computer Science, Norwegian University of Science and Technology · Department of Mathematical Sciences, Norwegian University of Science and Technology
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
May 13, 2026Ziyang You, Liling Zheng, Xiaoke Yang +1Backdoor Attacks Diffusion Models
School of Electronics, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou 350118, China · School of Humanities, Fujian University of Technology, Fuzhou 350118, China · Institute of Applied Physics and Materials Engineering, University of Macau, Macau 999078, China
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
May 12, 2026Ziyu Liu, Tao Li, Tianjie Ni +5LLM Backdoor Attacks Backdoor Attacks
School of Cyber Science and Engineering, Sichuan University, Chengdu, China · School of Computer Science, China West Normal University, Nanchong, China · School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, China
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
May 11, 2026Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu +2Backdoor Attacks Backdoor Attacks in Federated Learning
The University of Manchester, UK · Institute for Infocomm Research, A*STAR, Singapore · Monash University, Australia +1
Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors
May 8, 2026Lu Bowen, Xinyu Tang, Yin Yin Low +1Backdoor Attacks Elastic Weight Consolidation
Monash University
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
May 8, 2026Fan Yang, Binyan Xu, Di Tang +1Graph Neural Networks Backdoor Attacks
The Chinese University of Hong Kong · Sun Yat-Sen University
BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning
May 7, 2026Yinbo Yu, Xueyu Yin, Jiadai Wang +4Backdoor Attacks Backdoor Detection
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics · School of Cybersecurity, Northwestern Polytechnical University · School of Computer Science and Technology, Harbin Institute of Technology +1
Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
May 7, 2026Kealan Dunnett, Reza Arablouei, Dimity Miller +2Fine-Tuning Backdoor Attacks
Queensland University of Technology, Brisbane Australia · CSIRO, Pullenvale QLD, Australia
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
May 5, 2026Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo +3Backdoor Attacks
University of Wisconsin–Madison · Princeton University
CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
May 4, 2026Ji Guo, Xiaolong Qin, Cencen Liu +3VLM Robustness Adversarial Attacks on VLMs
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, China · School of Software Engineering, Chengdu University of Information Technology, China · The Hong Kong University of Science and Technology, China
TRAP: Tail-aware Ranking Attack for World-Model Planning
May 3, 2026Siyuan Duan, Ke Zhang, Xizhao LuoBackdoor Attacks World Model-Based Planning
Department of Computer Science and Technology, Soochow University Suzhou, China
Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
May 2, 2026Yi Yang, Jinyang Huang, Binbin Liu +5Backdoor Attacks Data Poisoning Attacks
School of Computer Science and Information Engineering Hefei University of Technology Hefei, Anhui, China · School of Information Science and Technology University of Science and Technology of China Hefei, Anhui, China · Faculty of Business Data Science Kansai University Japan +3
Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
Apr 25, 2026Xiao Yang, Yuni Lai, Gaolei Li +4Backdoor Attacks Adversarial Robustness
School of Computer Science, Shanghai Jiao Tong University, and Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai, China · Department of Computing, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong · Department of Electrical and Computer Engineering and Frost Institute for Data Science and Computing, University of Miami, Coral Gables, Florida 33146, USA
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
Apr 23, 2026Jiali Wei, Ming Fan, Guoheng Sun +3LLM Backdoor Attacks Backdoor Attacks
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China · Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, China
CSC: Turning the Adversary's Poison against Itself
Apr 23, 2026Yuchen Shi, Xin Guo, Huajie Chen +3Backdoor Attacks Backdoor Defense
Faculty of Data Science, City University of Macau, Taipa, Macau. · Faculty of Engineering and Information Technology, University of Technology Sydney, New South Wales, Australia.
PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
Apr 21, 2026Dazhuang Liu, Yanqi Qiao, Rui Wang +2Adversarial Attacks Vision Transformer
Delft University of Technology, Delft, the Netherlands. · University of Turku, Turku, Finland
SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
Mar 9, 2026Junxian Li, Tu Lan, Haozhen Tan +2Backdoor Attacks GUI Agents
School of Computer Science, Shanghai Jiao Tong University
TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion
Jan 23, 2026Saideep Sreekumar, Zeng Wang, Akashdeep Saha +6Backdoor Attacks Adversarial Robustness
NYU Abu Dhabi, Abu Dhabi, UAE · NYU Tandon School of Engineering, New York, USA
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
May 26, 2025Shijie Liu, Andrew C. Cullen, Paul Montague +2Adversarial Attacks Backdoor Attacks
School of Computing and Information Systems, University of Melbourne, Parkville, Australia · DST Group, Adelaide
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
May 22, 2025Thibaud Gloaguen, Mark Vero, Robin Staab +1LLM Backdoor Attacks Backdoor Attacks
ETH Zurich
Backdoor Attacks on Discrete Graph Diffusion Models
Mar 8, 2025Jiawen Wang, Samin Bin Karim, Yuan Hong +1Graph Generation Backdoor Attacks
Illinois Institute of Technology · University of Connecticut
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
Feb 29, 2024Pengzhou Cheng, Wei Du, Zongru Wu +4Language Model Pretraining LLM Backdoor Attacks
School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University · Department of Computer Science and Engineering Southern University of Science and Technology

May 19, 2026, cs.CRJ/K move · Enter open · S save

Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models

Kai Wang, Jiale Zhang, Chengcheng Zhu, Chuang Ma+1

Yangzhou University · Nanjing University · Chongqing University+1

Backdoor Attacks Diffusion Model Fine-Tuning T2I Diffusion Models

Open paper AskPDF arXiv

Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapted and redistributed by multiple independent parties, allowing multiple concept-specific trigger-target associations to accumulate in the same model. When these associations coexist, semantic conflicts can be amplified in the shared representation space, leading to cross-concept entanglement and degraded generation quality. Notably, instead of strengthening the attack, such accumulation can destabilize previously injected behaviors and reduce attack reliability. In this work, we systematically investigate backdoor attacks under this interference-prone setting and propose Hydra, a unified framework for robust and controlled multi-concept backdoor injection under cumulative and decentralized reuse. Our core insight is that stable backdoor injection under large-scale multi-concept settings requires explicitly constraining trigger semantics while coordinating cross-task interactions during optimization. Specifically, Hydra performs evolutionary trigger search in the text encoder space to identify triggers that are semantically aligned with their target concepts while remaining stable across other injected concepts. It further combines multi-task fine-tuning with trigger-clean regularization to improve training stability under dense multi-concept injection. Extensive experiments across multiple diffusion backbones under rigorous multi-concept settings show that Hydra maintains effective backdoor activation while preserving clean generation fidelity and image quality. For instance, across 8 attackers and 500 concept pairs, Hydra maintains ~95% ASR and strong clean generation.

Momentum

Related topics

Latest papers 87