BARBICAN study finds routed prompt-injection stages can look accurate by chance
Fixing a tokenizer raised arbitration AUC from 0.392 to 0.855 while system recall fell slightly.
Stories per day · 30 days
Relatedai-text-detection1barbican1fairness1interpretability1llm1mcp1model-evaluation1multi-armed-bandit1online-learning1prompt-injection1sparse-autoencoders1thompson-sampling1
4 stories, newest first · one card per story
Stories tagged #classifiers
Sparse autoencoders turn neural AI-text detectors into readable classifiers
Classifiers using only interpretable SAE features beat neural and stylometric detectors on out-of-distribution text.
Bayesian Learning to Select Fair Classifiers
Researchers use Thompson Sampling to pick classifiers that balance accuracy and subgroup fairness online.
Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers
Paper ties finite-time Lyapunov exponents of deep classifiers to decision-boundary geometry.