Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
cs.LG, cs.AI
Submitted: 2026-05-19
Updated: 2026-05-19
Code: https://github.com/cpdonline/cpdonline
Terminology
Sources
- Detecting Language Model Attacks with Perplexity
- Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- AI Alignment: A Comprehensive Survey
- Qwen2.5 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- Universal and Transferable Adversarial Attacks on Aligned Language 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