{"total":74,"rows":[{"id":"2110.11891","title":"On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning","created":"2021-10-22","cited_by_count":171,"area":"safety"},{"id":"2112.02918","title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","created":"2021-12-06","cited_by_count":127,"area":null},{"id":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"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":"2402.00751","title":"Fast Exact Unlearning for In-Context Learning Data for LLMs","created":"2024-02-01","cited_by_count":34,"area":"safety"},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2204.09092","title":"Indiscriminate Data Poisoning Attacks on Neural Networks","created":"2022-04-19","cited_by_count":25,"area":"safety"},{"id":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2210.09126","title":"Verifiable and Provably Secure Machine Unlearning","created":"2022-10-17","cited_by_count":25,"area":"safety"},{"id":"2307.00682","title":"Tools for Verifying Neural Models' Training Data","created":"2023-07-02","cited_by_count":22,"area":null},{"id":"2408.00929","title":"Verification of Machine Unlearning is Fragile","created":"2024-08-01","cited_by_count":21,"area":"safety"},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2207.11240","title":"Discrete Key-Value Bottleneck","created":"2022-07-22","cited_by_count":18,"area":null},{"id":"2304.10655","title":"The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions","created":"2023-04-20","cited_by_count":17,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","cited_by_count":17,"area":null},{"id":"2202.01838","title":"Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods","created":"2022-02-03","cited_by_count":16,"area":null},{"id":"2301.04017","title":"Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation","created":"2023-01-09","cited_by_count":16,"area":null},{"id":"2506.06151","title":"Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2025-06-06","cited_by_count":16,"area":"rag"},{"id":"2210.11334","title":"Proof of Unlearning: Definitions and Instantiation","created":"2022-10-20","cited_by_count":15,"area":"safety"},{"id":"2202.05470","title":"Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers","created":"2022-02-11","cited_by_count":14,"area":null},{"id":"2503.15293","title":"Test-Time Backdoor Detection for Object Detection Models","created":"2025-03-19","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":"2208.03567","title":"Proof-of-Learning is Currently More Broken Than You Think","created":"2022-08-06","cited_by_count":12,"area":null},{"id":"2303.00586","title":"FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling","created":"2023-03-01","cited_by_count":11,"area":null},{"id":"2307.00310","title":"Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD","created":"2023-07-01","cited_by_count":11,"area":null},{"id":"2402.06957","title":"Architectural Neural Backdoors from First Principles","created":"2024-02-10","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":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2201.11137","title":"Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization","created":"2022-01-26","cited_by_count":10,"area":null},{"id":"2206.02953","title":"Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization","created":"2022-06-07","cited_by_count":10,"area":null},{"id":"2210.00108","title":"ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2410.10128","title":"Edge Unlearning is Not \"on Edge\"! An Adaptive Exact Unlearning System on Resource-Constrained Devices","created":"2024-10-14","cited_by_count":9,"area":"safety"},{"id":"2106.06654","title":"Disrupting Model Training with Adversarial Shortcuts","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2501.06650","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","created":"2025-01-11","cited_by_count":7,"area":null},{"id":"2606.29554","title":"Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise","created":"2026-06-28","cited_by_count":7,"area":null},{"id":"2306.14043","title":"Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks","created":"2023-06-24","cited_by_count":6,"area":"safety"},{"id":"2509.14223","title":"Fresh in memory: Training-order recency is linearly encoded in language model activations","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2202.02510","title":"A Survey on Poisoning Attacks Against Supervised Machine Learning","created":"2022-02-05","cited_by_count":5,"area":null},{"id":"2209.15139","title":"Augmentation Backdoors","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2505.14832","title":"SEPS: A Separability Measure for Robust Unlearning in LLMs","created":"2025-05-20","cited_by_count":5,"area":"safety"},{"id":"2301.12318","title":"Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2408.06063","title":"TruVRF: Towards Triple-Granularity Verification on Machine Unlearning","created":"2024-08-12","cited_by_count":4,"area":"safety"},{"id":"2505.22778","title":"Machine Learning Models Have a Supply Chain Problem","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2406.12222","title":"BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2606.11660","title":"Bergson: An Open Source Library for Data Attribution","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2308.03999","title":"Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning","created":"2023-08-08","cited_by_count":2,"area":"lr"},{"id":"2309.01614","title":"Dropout Attacks","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2310.10124","title":"A Comprehensive Study of Privacy Risks in Curriculum Learning","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2404.11357","title":"Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2506.11402","title":"LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2601.21902","title":"Hardware-Triggered Backdoors","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2311.12715","title":"Attacks on fairness in Federated Learning","created":"2023-11-21","cited_by_count":1,"area":"safety"},{"id":"2412.02535","title":"Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2503.17578","title":"Large Language Models Can Verbatim Reproduce Long Malicious Sequences","created":"2025-03-21","cited_by_count":1,"area":"safety"},{"id":"2504.00170","title":"Backdoor Detection through Replicated Execution of Outsourced Training","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2504.14798","title":"RUB: Evaluating Residual Knowledge in Unlearned Models","created":"2025-04-21","cited_by_count":1,"area":"safety"},{"id":"2506.09923","title":"Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning","created":"2025-06-11","cited_by_count":1,"area":"safety"},{"id":"2212.04322","title":"Encrypted machine learning of molecular quantum properties","created":"2022-12-05","cited_by_count":0,"area":null},{"id":"2405.18549","title":"Learning from Uncertain Data: From Possible Worlds to Possible Models","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2411.17292","title":"TPCL: Task Progressive Curriculum Learning for Robust Visual Question Answering","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2505.06520","title":"PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks","created":"2025-05-10","cited_by_count":0,"area":"safety"},{"id":"2507.01607","title":"SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2509.07290","title":"zkUnlearner: A Zero-Knowledge Framework for Verifiable Unlearning with Multi-Granularity and Forgery-Resistance","created":"2025-09-08","cited_by_count":0,"area":"safety"},{"id":"2602.09182","title":"One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.04800","title":"Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation","created":"2026-04-06","cited_by_count":0,"area":"safety"},{"id":"2606.10091","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.14518","title":"Characterizing Privacy-Audit Alignment in Behavioral Audit of Machine Unlearning","created":"2026-06-12","cited_by_count":0,"area":"safety"},{"id":"2609.35528","title":"Let the Neurons Die: Exploiting ReLU-Induced Model Degradation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}