Data Poisoning Attacks

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

All topics

Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
Oct 7, 2026Qirun Zeng, Manhin Poon, Xiangxiang Dai +2Adversarial Attacks Multi-Armed Bandits
City University of Hong Kong, Hong Kong SAR, China · The Chinese University of Hong Kong, Hong Kong SAR, China · Nanyang Technological University, Singapore
Online AutoML: Evaluating Poisoning Attacks on Adversarial Training Defense Strategy in IoT Networks
Oct 5, 2026Chukwunonso Henry Nwokoye, Khalil El-Khatib, Li YangAdversarial Training Internet of Things
Faculty of Business and Information Technology, Ontario Tech University, Oshawa, Ontario, Canada · Department of Computer Science, Alex Ekwueme Federal University, Nigeria
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
Oct 1, 2026Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik +1Adversarial Robustness Data Poisoning Attacks
College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA · Department of Computer Science and Engineering, University of Louisville, Louisville, KY, USA · Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA
Let the Neurons Die: Exploiting ReLU-Induced Model Degradation
Sep 28, 2026Kexin Li, Wenjun Qiu, Joshua Abraham +2ReLU Neural Networks Adversarial Attacks
University of Toronto, Toronto, Ontario, Canada
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Sep 28, 2026Zihan Zhang, Shuangjie Yao, Zesen Liu +8LLM Security Data Poisoning Attacks
The Hong Kong University of Science and Technology · Tsinghua University
The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning
Sep 27, 2026Sae Furukawa, Alina OpreaSupervised Fine-Tuning Privacy Leakage in Language Models
Khoury College of Computer Sciences, Northeastern University
TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement
Sep 24, 2026Haoyang Li, Yaxin Xiao, Linyan Dai +5Multimodal Robustness Backdoor Attacks on VLMs
The Hong Kong Polytechnic University · Commonwealth Scientific and Industrial Research Organisation (CSIRO)
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems
Sep 22, 2026Yue Xing, Pengfei He, Zitao LiAI Agent Security Recommender Systems
Michigan State University
FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks
Sep 22, 2026Huigan Zheng, Jiaojiao Zhang, Yongxiang LiuAlgorithmic Fairness Adaptive Loss Weighting
Sun Yat-Sen University · Pengcheng Laboratory · Great Bay University
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia Smith +2LLM Backdoor Attacks Backdoor Attacks
Carnegie Mellon University · Anthropic
Empirical Evaluation of Data Poisoning Attacks in Supervised Learning
Sep 10, 2026Toshif Khan, Muhammad AbusaqerAdversarial Attacks Backdoor Attacks
Minot State University · Department of Math, Data & Technology Minot State University Minot, ND, 58707 · Trustworthy Language Intelligence Lab, Minot State University
Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks
Sep 9, 2026Ammar Kamoona, Sajad Koushkbaghi, Mahdi Jalili +2Cyber-Physical Systems Network Intrusion Detection
Powercor, Melbourne, VIC, Australia
An Efficient and Effective Agentic Group Shilling Attack on Recommender Systems
Sep 9, 2026Quoc Viet Nguyen, Trinh Pham, Viet Huynh +4Adversarial Attacks Recommender Systems
Griffith University, Australia · Edith Cowan University, Australia · The University of Queensland, Australia +1
Leveraging Imperfect Restoration for Data Availability Attack
Sep 7, 2026Yi Huang, Jeremy Styborski, Mingzhi Lyu +2Data Poisoning Attacks Unlearnable Examples
College of Computing and Data Science, Nanyang Technological University, Singapore · Rapid-Rich Object Search (ROSE) Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore
Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
Sep 5, 2026Zhongan Bi, Qiwen Wang, Jianrong Jiang +11LLM Agent Evaluation Web Search Agents
Zhejiang University · Ant Group
CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
Sep 2, 2026Varun Gadey, Ziad Marey, Alexandra DmitrienkoData Poisoning Attacks Software Security
University of Duisburg-Essen, Germany
Poisoning Attacks on the PGM-index
Sep 2, 2026Atsuki Sato, Martin Aumüller, Yusuke MatsuiData Poisoning Attacks
Graduate School of Information Science and Technology, The University of Tokyo · Algorithms Group, IT University of Copenhagen
VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models
Sep 1, 2026Zhiqi Huang, Vivek Datla, Zhichao Xu +3Learning to Rank RAG Poisoning Attacks
Capital One · University of Utah · Snowflake Inc.
Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning
Aug 31, 2026Fukang Zhu, Binbin Zhao, Ruixiao Lin +3Prompt Sensitivity AI Coding Agents
1Zhejiang University · 2State Key Laboratory of Internet Architecture, Tsinghua University
Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text
Aug 31, 2026Minkyung Cho, Jihyo Kim, SeungWoo Song +4Social Bias in Language Models LLM Security
KAIST · KAIST InnoCORE PRISM-AI Center · Department of Artificial Intelligence, Dankook University
Targeted Label-Flipping and Oversampling Attacks on Federated Conditional GANs
Aug 10, 2026Panav Shah, Avishek GhoshAdversarial Attacks Data Poisoning Attacks
Indian Institute of Technology, Bombay Mumbai, India
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks
Aug 10, 2026Yi Yang, Xiaoke Chen, Jinyang Huang +6Backdoor Attacks Data Selection
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China · John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China +1
TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning
Aug 7, 2026Yuhan Xie, Jingrong Huang, Chen LyuAdversarial Robustness Split Federated Learning
Shanghai University of Finance and Economics MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai, China
Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning
Aug 6, 2026Devharsh Trivedi, Nesrine Kaaniche, Nikos Triandopoulos +2Federated Learning Aggregation Byzantine-Robust Federated Learning
Department of Computer Science, Bowie State University, MD, USA · SAMOVAR, T´el´ecom SudParis, Institut Polytechnique de Paris, Palaiseau, France · Department of Computer Science, Brown University, RI, USA +1
Breadcrumbing Search Agents
Aug 5, 2026Xuebin Li, Hanqing Zhao, Siyuan Liang +4Adversarial Attacks Web Search Agents
School of Cyber Science and Technology, University of Science and Technology of China · College of Computing and Data Science, Nanyang Technological University
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
Jul 30, 2026Puning Zhao, Zhikun Zhang, Shaowei Wang +5Sparse Recovery Differential Privacy
Shenzhen Campus of Sun Yat-sen University · Zhejiang University · Guangzhou University +2
Lilith: Backdoor Generalization under Training-Inference Trigger Shift
Jul 28, 2026Zhou Feng, Jiahao Chen, Chunyi Zhou +6Backdoor Attacks Data Poisoning Attacks
Zhejiang University College of Computer Science and Technology Hangzhou, China · Zhejiang University School of Software Technology Hangzhou, China · Chongqing University School of Big Data & Software Engineering Chongqing, China +1
Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning
Jul 25, 2026Adhyyan Narang, Artin Tajdini, Claire Zhang +1LLM Alignment Emergent Misalignment in Language Models
University of Washington
Data-Poisoning Audits for Causal Effect Estimation
Jul 22, 2026Kwangho KimCausal Effect Estimation Data Poisoning Attacks
Department of Statistics, Korea University, Seoul, Republic of Korea
Natural Backdoor Attacks on Speech Recognition Models
Jul 17, 2026Jinwen Xin, Xixiang Lyu, Jing MaBackdoor Attacks Automatic Speech Recognition
School of Cyber Engineering, Xidian University, Xi’an, China

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards

Qirun Zeng, Manhin Poon, Xiangxiang Dai, Qixin Zhang+1

City University of Hong Kong, Hong Kong SAR, China · The Chinese University of Hong Kong, Hong Kong SAR, China · Nanyang Technological University, Singapore

Adversarial Attacks Multi-Armed Bandits Data Poisoning Attacks

Open paper AskPDF arXiv

Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this by suppressing non-target arms. In practice, however, manipulation such as fake reviews often directly promotes the target item. We study this gap through bounded offline attacks on warm-start bandits, where an attacker can inject only valid action-reward pairs into the warm-start history before deployment. We show that target promotion is not merely a heuristic: when the target arm lies near the lower reward boundary, any order-optimal-cost attack against UCB that makes it selected in nearly all online rounds must allocate a nonvanishing fraction of its cost to the target arm. We then design an attack that achieves the optimal sublinear cost and characterize its allocation between target promotion and non-target suppression. We further extend the attack to Thompson Sampling,

ε

-greedy, and a broader class of bandit algorithms. Experiments on real-world and synthetic data validate the effectiveness of our attacks.

Momentum

Related topics

Latest papers 93