← Back to all news
arXiv AI

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification

ReCAST is a framework that trains a small student model to classify obfuscated Chinese SMS messages by first learning to detect obfuscated spans, predict obfuscation types, and restore the original text using knowledge distilled from a large teacher model. The student model then performs risk classification, achieving better performance than directly trained baselines on a real-world Chinese SMS benchmark. This approach demonstrates that restoration-aware distillation can produce robust, production‑ready SMS risk classifiers with reduced model size.

Related stories

arXiv Computation and Language
Sep 28

Prompt Injection Detection for Email Agents Through Attack Chain Modeling

The paper introduces a prompt‑injection detection framework for email assistants that models attacks as a chain of stages. It combines a text detector, stage‑specific verifiers, rule‑based risk signals, user intent consistency checks, and a logistic decision policy. Experiments on five benchmarks show the framework outperforms pretrained detectors, achieving a mean F1 of 0.406 versus 0.216, and demonstrate that training on benign emails resembling attacks reduces false alarms.

By Ahmad Hashmi, Dhyey Patel, Yunting Yin
llmsagentsnlpbenchmarks
More like this →
arXiv Machine Learning
Oct 3

Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers

The paper reports a reproducible study of evasion attacks on image and text classifiers. A compact convolutional network on MNIST achieved 98.63% clean accuracy but dropped to 60.20% under FGSM with ε=0.15 and 1.72% with ε=0.30, while PGD reduced accuracy to 32.47% and 0.41%; a bit‑depth‑reduction defense only partially restored performance. In contrast, a DistilBERT model fine‑tuned on the SMS Spam Collection reached 98.75% accuracy and 94.96% F1‑score, yet a sequence of predefined perturbations produced only modest probability shifts and did not flip spam to ham predictions.

By Parker Hummel (Minot State University), Ryne Skabo (Minot State University), Muhammad Abusaqer (Minot State University)
computer-visionnlpfine-tuningsafety
More like this →
arXiv AI
Aug 3

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

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.

By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu
llmsnlpreinforcement-learningfine-tuningbenchmarkssafety
More like this →
arXiv Computation and Language
Aug 24

Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift

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.

By San Kim, JinYeong Bak
More like this →
arXiv Machine Learning
Jun 3

Backdooring Masked Diffusion Language Models

arXiv:2605. 19262v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored.

By Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang, Pin-Yu Chen, Shengwei An
llmsdiffusionfine-tuning
More like this →