{"total":89,"rows":[{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235,"area":null},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2104.03413","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","created":"2021-04-07","cited_by_count":161,"area":"safety"},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"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":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79,"area":null},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"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":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2108.02488","title":"Poison Ink: Robust and Invisible Backdoor Attack","created":"2021-08-05","cited_by_count":50,"area":null},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","cited_by_count":43,"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":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","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":"2303.06854","title":"Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks","created":"2023-03-13","cited_by_count":31,"area":"mllm"},{"id":"2312.00050","title":"Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift","created":"2023-11-27","cited_by_count":31,"area":"diffusion"},{"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":"2106.07085","title":"Survey: Image Mixing and Deleting for Data Augmentation","created":"2021-06-13","cited_by_count":26,"area":null},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2208.08052","title":"Imperceptible and Robust Backdoor Attack in 3D Point Cloud","created":"2022-08-17","cited_by_count":25,"area":null},{"id":"2109.00685","title":"Excess Capacity and Backdoor Poisoning","created":"2021-09-02","cited_by_count":24,"area":null},{"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":"2207.10825","title":"Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation","created":"2022-07-22","cited_by_count":20,"area":null},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2304.01482","title":"Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning","created":"2023-04-04","cited_by_count":20,"area":null},{"id":"2211.12044","title":"Backdoor Cleansing with Unlabeled Data","created":"2022-11-22","cited_by_count":17,"area":null},{"id":"2302.02300","title":"Run-Off Election: Improved Provable Defense against Data Poisoning Attacks","created":"2023-02-05","cited_by_count":17,"area":"safety"},{"id":"2202.10627","title":"On the Effectiveness of Adversarial Training against Backdoor Attacks","created":"2022-02-22","cited_by_count":16,"area":null},{"id":"2301.06241","title":"BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense","created":"2023-01-16","cited_by_count":15,"area":null},{"id":"2406.06186","title":"A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks","created":"2024-06-10","cited_by_count":15,"area":"safety"},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2403.10717","title":"Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2403.17188","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","created":"2024-03-25","cited_by_count":13,"area":null},{"id":"2201.13329","title":"Can Adversarial Training Be Manipulated By Non-Robust Features?","created":"2022-01-31","cited_by_count":12,"area":null},{"id":"2210.06428","title":"Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork","created":"2022-10-12","cited_by_count":12,"area":null},{"id":"2210.10886","title":"Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis","created":"2022-10-19","cited_by_count":12,"area":"safety"},{"id":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"area":null},{"id":"2406.15093","title":"ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification","created":"2024-06-21","cited_by_count":9,"area":null},{"id":"2210.13815","title":"FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2106.07214","title":"Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions","created":"2021-06-14","cited_by_count":5,"area":null},{"id":"2209.15139","title":"Augmentation Backdoors","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2406.05826","title":"PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2505.19532","title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":"deeprl"},{"id":"2103.15918","title":"MISA: Online Defense of Trojaned Models using Misattributions","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2201.12211","title":"Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire","created":"2022-01-28","cited_by_count":4,"area":"safety"},{"id":"2203.03692","title":"Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks","created":"2022-03-07","cited_by_count":4,"area":"safety"},{"id":"2301.08751","title":"Towards Understanding How Self-training Tolerates Data Backdoor Poisoning","created":"2023-01-20","cited_by_count":4,"area":null},{"id":"2404.11265","title":"The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data","created":"2024-04-17","cited_by_count":4,"area":"safety"},{"id":"2412.00727","title":"Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP","created":"2024-12-01","cited_by_count":4,"area":"mllm"},{"id":"2110.04571","title":"Widen The Backdoor To Let More Attackers In","created":"2021-10-09","cited_by_count":3,"area":null},{"id":"2205.09891","title":"Interpolating Compressed Parameter Subspaces","created":"2022-05-19","cited_by_count":3,"area":null},{"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":"2311.14948","title":"Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective","created":"2023-11-25","cited_by_count":2,"area":"mllm"},{"id":"2406.17277","title":"Securing Voice Authentication Applications Against Targeted Data Poisoning","created":"2024-06-25","cited_by_count":2,"area":"safety"},{"id":"2409.00863","title":"Fisher Information guided Purification against Backdoor Attacks","created":"2024-09-01","cited_by_count":2,"area":null},{"id":"2410.12955","title":"Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2410.21453","title":"Inverting Gradient Attacks Makes Powerful Data Poisoning","created":"2024-10-28","cited_by_count":2,"area":"safety"},{"id":"2411.09776","title":"Combining Machine Learning Defenses without Conflicts","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2108.04206","title":"Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks","created":"2021-08-09","cited_by_count":1,"area":"safety"},{"id":"2205.04411","title":"Model-Contrastive Learning for Backdoor Defense","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2205.13613","title":"Circumventing Backdoor Defenses That Are Based on Latent Separability","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2206.07018","title":"Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2306.17441","title":"Efficient Backdoor Removal Through Natural Gradient Fine-tuning","created":"2023-06-30","cited_by_count":1,"area":null},{"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":"2311.06227","title":"Does Differential Privacy Prevent Backdoor Attacks in Practice?","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2403.13523","title":"Have You Poisoned My Data? Defending Neural Networks against Data Poisoning","created":"2024-03-20","cited_by_count":1,"area":"safety"},{"id":"2404.14042","title":"CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction","created":"2024-04-22","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":"2410.01128","title":"Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers","created":"2024-10-01","cited_by_count":1,"area":"safety"},{"id":"2411.13459","title":"SoK: A Systems Perspective on Compound AI Threats and Countermeasures","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2301.07474","title":"Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2306.01983","title":"Mitigating Backdoor Attack Via Prerequisite Transformation","created":"2023-06-03","cited_by_count":0,"area":null},{"id":"2306.03726","title":"Exploring Model Dynamics for Accumulative Poisoning Discovery","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2309.17278","title":"Toward Robust Recommendation via Real-time Vicinal Defense","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2312.13863","title":"Manipulating Trajectory Prediction with Backdoors","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2405.06073","title":"Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search","created":"2024-05-09","cited_by_count":0,"area":"safety"},{"id":"2405.16488","title":"Partial train and isolate, mitigate backdoor attack","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2405.19376","title":"PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models","created":"2024-05-28","cited_by_count":0,"area":"safety"},{"id":"2410.05284","title":"Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery","created":"2024-09-29","cited_by_count":0,"area":"safety"},{"id":"2502.10490","title":"A Robust Attack: Displacement Backdoor Attack","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.20925","title":"Prototype Guided Backdoor Defense","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2506.15112","title":"PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning","created":"2025-06-18","cited_by_count":0,"area":"safety"},{"id":"2601.02682","title":"Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learning","created":"2026-01-06","cited_by_count":0,"area":null}],"next_cursor":null}