{"total":14,"rows":[{"id":"2412.17522","title":"DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak","created":"2024-12-23","cited_by_count":9,"area":"diffusion"},{"id":"2509.23286","title":"A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models","created":"2025-09-27","cited_by_count":9,"area":"diffusion"},{"id":"2512.24143","title":"Activation Steering for Masked Diffusion Language Models","created":"2025-12-30","cited_by_count":9,"area":"diffusion"},{"id":"2511.19558","title":"SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation","created":"2025-11-24","cited_by_count":2,"area":"diffusion"},{"id":"2604.08557","title":"Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models","created":"2026-03-17","cited_by_count":2,"area":"diffusion"},{"id":"2605.08116","title":"The Safety-Aware Denoiser for Text Diffusion Models","created":"2026-04-28","cited_by_count":2,"area":"diffusion"},{"id":"2606.00023","title":"TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models","created":"2026-04-15","cited_by_count":2,"area":"diffusion"},{"id":"2608.20123","title":"Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo","created":"2026-08-20","cited_by_count":2,"area":"diffusion"},{"id":"2602.02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","created":"2026-02-01","cited_by_count":1,"area":"diffusion"},{"id":"2605.13043","title":"Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models","created":"2026-05-13","cited_by_count":1,"area":"diffusion"},{"id":"2609.00495","title":"Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models","created":"2026-08-31","cited_by_count":0,"area":"diffusion"},{"id":"2609.30841","title":"Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis","created":"2026-09-25","cited_by_count":0,"area":"diffusion"},{"id":"2609.33634","title":"Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.17636","title":"The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}