The paper introduces MOSAIC, a large adversarial benchmark for detecting AI-generated text, and presents NeuroStat, a new framework that combines token‑level probabilistic logits with deep semantic hidden states from a single language model. NeuroStat fuses these signals via Macro‑State Residual Modulation and uses orthogonal and contrastive losses to learn complementary representations. Experiments show that NeuroStat outperforms existing methods on MOSAIC, achieving superior robustness against adversarial attacks.
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.
arXiv:2604. 25860v2 Announce Type: replace-cross Abstract: Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints.
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.
The paper introduces a new evaluation setting called scenario‑level out‑of‑distribution (SL‑OOD) detection for SMS and voice phishing, where entire attack scenarios are omitted from training while the label space stays fixed. It shows that high in‑distribution performance does not guarantee robustness to unseen scenarios, attributing this to scenario memorization. The authors propose ECoG, an evidence‑consistent generative framework that uses evidence‑span supervision and a rationale‑label consistency objective, achieving notable improvements in Macro‑F1, reduced prediction‑rationale inconsistency, and higher token‑level overlap with reference evidence.
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.
arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.
arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.
arXiv:2606. 14060v1 Announce Type: new Abstract: Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors.
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.