arXiv Machine Learning By Jun Wen Leong

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

Read the original on arXiv Machine Learning →

arXiv:2606. 11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 30

Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks

arXiv:2607. 26574v1 Announce Type: cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a rare language, code, or an image of text slips past a guard that would block it in plain language -- the decode gap.

By Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Zijian Xiao, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
arXiv AI
Jun 16

Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale

arXiv:2512. 19011v3 Announce Type: replace-cross Abstract: Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned transformers and LLM-as-a-judge pipelines.

By Vasudev Majhi, Dhruv Gupta, Advait Singh, Matthew Barker, Dhruv Kumar
arXiv Machine Learning
Jun 26

CALIBURN: Operationally Calibrated Streaming Intrusion Detection with Regime-Dependent Conformal Risk Control

arXiv:2605. 24696v2 Announce Type: replace-cross Abstract: Streaming intrusion detection systems must process flows continuously under bounded memory, yet most leave alerting-threshold selection as a post-hoc tuning problem incompatible with production, where operators commit in advance to alert budgets, misclassification costs, and Service Level Objectives.

By Michel A. Youssef