{"total":22,"rows":[{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110,"area":"safety"},{"id":"2304.03400","title":"RoSteALS: Robust Steganography using Autoencoder Latent Space","created":"2023-04-06","cited_by_count":57,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2408.05868","title":"LaWa: Using Latent Space for In-Generation Image Watermarking","created":"2024-08-11","cited_by_count":28,"area":"safety"},{"id":"2306.01272","title":"DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detection","created":"2023-06-02","cited_by_count":9,"area":"safety"},{"id":"2406.19395","title":"Dataset Size Recovery from LoRA Weights","created":"2024-06-27","cited_by_count":7,"area":"safety"},{"id":"2506.23484","title":"TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity","created":"2025-06-30","cited_by_count":7,"area":"safety"},{"id":"2405.10612","title":"Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers","created":"2024-05-17","cited_by_count":5,"area":"safety"},{"id":"2503.01839","title":"Jailbreaking Safeguarded Text-to-Image Models via Large Language Models","created":"2025-03-03","cited_by_count":5,"area":"safety"},{"id":"2503.00531","title":"GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model","created":"2025-03-01","cited_by_count":4,"area":"safety"},{"id":"2405.16596","title":"Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generation","created":"2024-05-26","cited_by_count":3,"area":"safety"},{"id":"2603.26316","title":"SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning","created":"2026-03-27","cited_by_count":3,"area":"safety"},{"id":"2412.16512","title":"TrojFlow: Flow Models are Natural Targets for Trojan Attacks","created":"2024-12-21","cited_by_count":1,"area":"safety"},{"id":"2502.07845","title":"Spread them Apart: Towards Robust Watermarking of Generated Content","created":"2025-02-11","cited_by_count":1,"area":"safety"},{"id":"2512.01314","title":"TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance","created":"2025-12-01","cited_by_count":1,"area":"safety"},{"id":"2603.05921","title":"BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation","created":"2026-03-06","cited_by_count":1,"area":"safety"},{"id":"2603.27513","title":"Understanding Semantic Perturbations on In-Processing Generative Image Watermarks","created":"2026-03-29","cited_by_count":1,"area":"safety"},{"id":"2605.09203","title":"Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2604.15967","title":"When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2609.39024","title":"Persistent Watermarking of Text-to-Image Models","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}