arXiv AI August 12, 2026 By Jinmo Han, Jimin Hong, Chanyeong Moon, Ju Yeon Kang, Seonuk Kim, Nam Soo Kim

MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection

arXiv:2608. 10459v1 Announce Type: cross Abstract: As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing styles, domains, languages, and generator models.

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

arXiv Machine Learning

Aug 7

Robust Context-Aware Detection of Malicious Instructions in Text

arXiv:2608. 05430v1 Announce Type: cross Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks.

By Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik

llms rag agents computer-vision benchmarks safety

arXiv Machine Learning

Jun 15

Non-Parametric Machine Text Detection via Multi-View Gaussian Processes

arXiv:2606. 14060v1 Announce Type: new Abstract: Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors.

By Aleem Khan, Nicholas Andrews

llms benchmarks safety

arXiv AI

Jul 17

T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting

arXiv:2607. 14113v1 Announce Type: cross Abstract: While many AI-generated text (AIGT) detectors achieve strong performance on clean inputs, their accuracy degrades significantly under light paraphrasing, word substitutions, character edits, and distribution shifts.

By Gayan K. Kulatilleke, Mahsa Baktashmotlagh, Siamak Layeghy, Marius Portmann

llms rag benchmarks safety

arXiv AI

Jul 1

Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks

arXiv:2606. 31074v1 Announce Type: cross Abstract: Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics.

By Guangsheng Bao, Lihua Rong, Yanbin Zhao, Xiao Yu, Qiji Zhou, Yue Zhang

benchmarks safety

arXiv AI

Jun 8

SV-Detect: AI-generated Text Detection with Steering Vectors

arXiv:2606. 07313v1 Announce Type: cross Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks.

By Mikhail Vishnyakov, Tatiana Gaintseva

llms safety

arXiv AI

Aug 11

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision

arXiv:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.

By Guy Azov, Ofer Rivlin, Guy Shtar

llms multimodal

Related stories

Robust Context-Aware Detection of Malicious Instructions in Text

Non-Parametric Machine Text Detection via Multi-View Gaussian Processes

T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting

Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks

SV-Detect: AI-generated Text Detection with Steering Vectors

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision