Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/eladd-ai/latent-undertow
Sources
- When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
- Building Production-Ready Probes For Gemini
- Detecting High-Stakes Interactions with Activation Probes
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
- Investigating task-specific prompts and sparse autoencoders for activation monitoring
- Representation Engineering: A Top-Down Approach to AI Transparency
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