Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents
cs.LG, cs.CR
Submitted: 2026-10-10
Updated: 2026-10-10
Project page: http://www.informations.com
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Agent Laboratory: Using LLM Agents as Research Assistants
- Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
- The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
- Defeating Prompt Injections by Design
- Simple and Effective Masked Diffusion Language Models
- DiffusionGemma Technical Report
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Concrete Score Matching: Generalized Score Matching for Discrete Data
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
- Simple Guidance Mechanisms for Discrete Diffusion Models
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- Constrained Discrete Diffusion
- Large Language Diffusion Models
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
- DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
- Dream 7B: Diffusion Large Language Models
- Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
- Simple Self-Conditioning Adaptation for Masked Diffusion Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks