{"total":16,"rows":[{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2202.03335","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","created":"2022-02-07","cited_by_count":45,"area":"safety"},{"id":"2102.04351","title":"Generating Fake Cyber Threat Intelligence Using Transformer-Based Models","created":"2021-02-08","cited_by_count":29,"area":"safety"},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"},{"id":"2407.01919","title":"A Method to Facilitate Membership Inference Attacks in Deep Learning Models","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"id":"2412.02432","title":"Improved Localized Machine Unlearning Through the Lens of Memorization","created":"2024-12-03","cited_by_count":6,"area":"safety"},{"id":"2407.12069","title":"Unlearning Personal Data from a Single Image","created":"2024-07-16","cited_by_count":4,"area":"safety"},{"id":"2504.13610","title":"Fairness and Robustness in Machine Unlearning","created":"2025-04-18","cited_by_count":4,"area":"safety"},{"id":"2502.12464","title":"SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models","created":"2025-02-18","cited_by_count":3,"area":"safety"},{"id":"2605.03058","title":"Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation","created":"2026-05-04","cited_by_count":2,"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":"2505.10351","title":"A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability","created":"2025-05-15","cited_by_count":1,"area":"safety"},{"id":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2605.14686","title":"ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators","created":"2026-05-14","cited_by_count":0,"area":"safety"},{"id":"2609.11490","title":"Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints","created":"2026-09-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}