{"total":120,"rows":[{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269,"area":null},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119,"area":null},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2106.08970","title":"Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch","created":"2021-06-16","cited_by_count":102,"area":"safety"},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2112.12376","title":"Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization","created":"2021-12-23","cited_by_count":76,"area":null},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2307.14192","title":"Unveiling Security, Privacy, and Ethical Concerns of ChatGPT","created":"2023-07-26","cited_by_count":53,"area":null},{"id":"2109.08266","title":"Hard to Forget: Poisoning Attacks on Certified Machine Unlearning","created":"2021-09-17","cited_by_count":52,"area":"safety"},{"id":"2311.13127","title":"MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning","created":"2023-11-22","cited_by_count":44,"area":"diffusion"},{"id":"2212.10717","title":"Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks","created":"2022-12-21","cited_by_count":43,"area":"safety"},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2110.06904","title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks","created":"2021-10-13","cited_by_count":40,"area":"safety"},{"id":"2301.13838","title":"Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression","created":"2023-01-31","cited_by_count":39,"area":null},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37,"area":"safety"},{"id":"2301.01217","title":"Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples","created":"2022-12-31","cited_by_count":36,"area":null},{"id":"2103.02683","title":"Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release","created":"2021-02-16","cited_by_count":35,"area":null},{"id":"2103.02079","title":"DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations","created":"2021-03-02","cited_by_count":34,"area":null},{"id":"2211.00463","title":"Amplifying Membership Exposure via Data Poisoning","created":"2022-11-01","cited_by_count":34,"area":"safety"},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2210.09194","title":"Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class","created":"2022-10-17","cited_by_count":33,"area":null},{"id":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32,"area":null},{"id":"2201.02873","title":"LoMar: A Local Defense Against Poisoning Attack on Federated Learning","created":"2022-01-08","cited_by_count":31,"area":null},{"id":"2210.09671","title":"Not All Poisons are Created Equal: Robust Training against Data Poisoning","created":"2022-10-18","cited_by_count":30,"area":"safety"},{"id":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30,"area":"safety"},{"id":"2205.12141","title":"One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks","created":"2022-05-24","cited_by_count":29,"area":null},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","cited_by_count":28,"area":null},{"id":"2204.09092","title":"Indiscriminate Data Poisoning Attacks on Neural Networks","created":"2022-04-19","cited_by_count":25,"area":"safety"},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2102.13624","title":"What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning","created":"2021-02-26","cited_by_count":22,"area":"safety"},{"id":"2208.10224","title":"Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks","created":"2022-08-14","cited_by_count":21,"area":"safety"},{"id":"2406.16565","title":"Noisy Neighbors: Efficient membership inference attacks against LLMs","created":"2024-06-24","cited_by_count":21,"area":"safety"},{"id":"2503.22759","title":"Data Poisoning in Deep Learning: A Survey","created":"2025-03-27","cited_by_count":20,"area":"safety"},{"id":"2211.12005","title":"Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors","created":"2022-11-22","cited_by_count":19,"area":null},{"id":"2410.08190","title":"Poison-splat: Computation Cost Attack on 3D Gaussian Splatting","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2202.08578","title":"An Equivalence Between Data Poisoning and Byzantine Gradient Attacks","created":"2022-02-17","cited_by_count":16,"area":"safety"},{"id":"2205.13176","title":"On Collective Robustness of Bagging Against Data Poisoning","created":"2022-05-26","cited_by_count":16,"area":"safety"},{"id":"2210.05929","title":"Few-shot Backdoor Attacks via Neural Tangent Kernels","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2312.08898","title":"Detection and Defense of Unlearnable Examples","created":"2023-12-14","cited_by_count":13,"area":null},{"id":"2107.03919","title":"Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning","created":"2021-07-08","cited_by_count":11,"area":"safety"},{"id":"2206.00700","title":"RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2406.14095","title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2106.09993","title":"Accumulative Poisoning Attacks on Real-time Data","created":"2021-06-18","cited_by_count":10,"area":null},{"id":"2111.13244","title":"Going Grayscale: The Road to Understanding and Improving Unlearnable Examples","created":"2021-11-25","cited_by_count":10,"area":null},{"id":"2305.14851","title":"Sharpness-Aware Data Poisoning Attack","created":"2023-05-24","cited_by_count":10,"area":"safety"},{"id":"2401.01549","title":"Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction","created":"2024-01-03","cited_by_count":10,"area":null},{"id":"2311.11995","title":"BrainWash: A Poisoning Attack to Forget in Continual Learning","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2408.08143","title":"Unlearnable Examples Detection via Iterative Filtering","created":"2024-08-15","cited_by_count":9,"area":"safety"},{"id":"2105.10948","title":"Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters","created":"2021-05-23","cited_by_count":8,"area":null},{"id":"2106.06654","title":"Disrupting Model Training with Adversarial Shortcuts","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2202.03576","title":"Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations","created":"2022-02-03","cited_by_count":7,"area":null},{"id":"2208.13904","title":"Reducing Certified Regression to Certified Classification for General Poisoning Attacks","created":"2022-08-29","cited_by_count":7,"area":null},{"id":"2210.09305","title":"Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning","created":"2022-10-17","cited_by_count":7,"area":"safety"},{"id":"2212.01082","title":"Membership Inference Attacks Against Semantic Segmentation Models","created":"2022-12-02","cited_by_count":7,"area":"safety"},{"id":"2110.15444","title":"10 Security and Privacy Problems in Large Foundation Models","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2306.15268","title":"Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?","created":"2023-06-27","cited_by_count":6,"area":null},{"id":"2107.10302","title":"Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2307.07328","title":"Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2402.02951","title":"Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2407.10867","title":"Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks","created":"2024-07-15","cited_by_count":5,"area":null},{"id":"2505.16567","title":"Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning","created":"2025-05-22","cited_by_count":5,"area":"safety"},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2602.09987","title":"Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions","created":"2026-02-10","cited_by_count":5,"area":null},{"id":"2603.04731","title":"When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2310.03125","title":"Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2310.07632","title":"Prompt Backdoors in Visual Prompt Learning","created":"2023-10-11","cited_by_count":4,"area":"safety"},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2408.15591","title":"VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2511.00446","title":"ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training","created":"2025-11-01","cited_by_count":4,"area":"mllm"},{"id":"2306.01613","title":"Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization","created":"2023-06-02","cited_by_count":3,"area":"safety"},{"id":"2307.01073","title":"What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?","created":"2023-07-03","cited_by_count":3,"area":null},{"id":"2309.16487","title":"Towards Poisoning Fair Representations","created":"2023-09-28","cited_by_count":3,"area":"safety"},{"id":"2405.18627","title":"PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics","created":"2024-05-28","cited_by_count":3,"area":"diffusion"},{"id":"2409.17328","title":"The poison of dimensionality","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2503.01896","title":"Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2410.21453","title":"Inverting Gradient Attacks Makes Powerful Data Poisoning","created":"2024-10-28","cited_by_count":2,"area":"safety"},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2305.09671","title":"Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks","created":"2023-05-07","cited_by_count":1,"area":"safety"},{"id":"2309.08549","title":"HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks","created":"2023-09-15","cited_by_count":1,"area":"safety"},{"id":"2310.13019","title":"Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2311.11544","title":"Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2403.11981","title":"Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2409.13004","title":"Data Poisoning and Leakage Analysis in Federated Learning","created":"2024-09-19","cited_by_count":1,"area":"safety"},{"id":"2410.08872","title":"Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2412.03908","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","created":"2024-12-05","cited_by_count":1,"area":"safety"},{"id":"2506.13205","title":"Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents","created":"2025-06-16","cited_by_count":1,"area":"mllm"},{"id":"2602.10457","title":"Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.29108","title":"Efficient Bilevel Optimization with KFAC-Based Hypergradients","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2210.11264","title":"Detecting Backdoors in Deep Text Classifiers","created":"2022-10-11","cited_by_count":0,"area":"safety"},{"id":"2212.02582","title":"Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning","created":"2022-12-05","cited_by_count":0,"area":"safety"},{"id":"2307.00456","title":"Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data","created":"2023-07-02","cited_by_count":0,"area":null},{"id":"2309.13579","title":"Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models","created":"2023-09-24","cited_by_count":0,"area":"safety"},{"id":"2312.01281","title":"Mendata: A Framework to Purify Manipulated Training Data","created":"2023-12-03","cited_by_count":0,"area":null},{"id":"2403.16365","title":"Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion","created":"2024-03-25","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}