Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- LLM Jailbreak Detection for (Almost) Free!
- A Survey on Diffusion Language Models
- DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
- Scaling up Masked Diffusion Models on Text
- Instruction Tuning with GPT-4
- Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
- MMaDA: Multimodal Large Diffusion Language Models
- Dream 7B: Diffusion Large Language Models
- Discrete Diffusion in Large Language and Multimodal Models: A Survey
- Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
- LLaDA-MoE: A Sparse MoE Diffusion Language Model
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection