Image de couverture de livre

Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Yangshijie, Wang, Xinda, Liu, Jialin, Wang, Wenqiang, Ma, Zhicong, Jia, Xingxing
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
par: Zhang, Yangshijie
Publié: (2025)

No Query, No Access
par: Wang, Wenqiang, et autres
Publié: (2025)

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
par: Wang, Xinda, et autres
Publié: (2025)

Incomplete In-context Learning
par: Wang, Wenqiang, et autres
Publié: (2025)

Generative Adversarial Reviews: When LLMs Become the Critic
par: Bougie, Nicolas, et autres
Publié: (2024)

When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
par: Liu, Ziyu, et autres
Publié: (2026)

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
par: Wang, Wenqiang, et autres
Publié: (2025)

Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
par: Xu, Qianqiao, et autres
Publié: (2024)

SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
par: Liu, Han, et autres
Publié: (2026)

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
par: Liu, Han, et autres
Publié: (2024)

Fast Adversarial Training against Textual Adversarial Attacks
par: Yang, Yichen, et autres
Publié: (2024)

Chain-of-Thought Unfaithfulness as Disguised Accuracy
par: Bentham, Oliver, et autres
Publié: (2024)

HauntAttack: When Attack Follows Reasoning as a Shadow
par: Ma, Jingyuan, et autres
Publié: (2025)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
par: Wei, Jiali, et autres
Publié: (2026)

Combating Adversarial Attacks with Multi-Agent Debate
par: Chern, Steffi, et autres
Publié: (2024)

Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
par: Liu, Geng, et autres
Publié: (2026)

When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models
par: Shamsi, Zafir, et autres
Publié: (2026)

InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
par: InternAgent Team, et autres
Publié: (2025)

$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models
par: Xu, Yue, et autres
Publié: (2024)

Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification
par: Li, Yanxi, et autres
Publié: (2025)

When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
par: Wang, Yunfei, et autres
Publié: (2026)

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
par: Jing, Liqiang, et autres
Publié: (2024)

Code-Style In-Context Learning for Knowledge-Based Question Answering
par: Nie, Zhijie, et autres
Publié: (2023)

Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models
par: Wang, Jialin, et autres
Publié: (2024)

Implicit Sentiment Analysis Based on Chain of Thought Prompting
par: Duan, Zhihua, et autres
Publié: (2024)

STACK: Adversarial Attacks on LLM Safeguard Pipelines
par: McKenzie, Ian R., et autres
Publié: (2025)

Adversarial Attacks and Defense for Conversation Entailment Task
par: Yang, Zhenning, et autres
Publié: (2024)

Thinkless: LLM Learns When to Think
par: Fang, Gongfan, et autres
Publié: (2025)

Adversarial Attacks Against Automated Fact-Checking: A Survey
par: Liu, Fanzhen, et autres
Publié: (2025)

PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
par: Zhao, Chenzhuo, et autres
Publié: (2025)

NILC: Discovering New Intents with LLM-assisted Clustering
par: Wang, Hongtao, et autres
Publié: (2025)

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
par: Sheng, Leheng, et autres
Publié: (2026)

From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
par: Liu, Junhua, et autres
Publié: (2024)

A Generative Adversarial Attack for Multilingual Text Classifiers
par: Roth, Tom, et autres
Publié: (2024)

Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection
par: Park, Sungwon, et autres
Publié: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
par: Liu, Fan, et autres
Publié: (2024)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
par: Xiao, Yuxin, et autres
Publié: (2025)

Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline
par: Shi, Yuanchen, et autres
Publié: (2024)

REIC: RAG-Enhanced Intent Classification at Scale
par: Zhang, Ziji, et autres
Publié: (2025)

Respond Beyond Language: A Benchmark for Video Generation in Response to Realistic User Intents
par: Wang, Shuting, et autres
Publié: (2025)