Copertina

Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kang, Jingyi, Lu, Junyu, Xu, Bo, Wang, Hongbo, zong, Linlin, Lee, Roy Ka-Wei, Lin, Hongfei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Comprehensive Detection of Chinese Harmful Memes
di: Lu, Junyu, et al.
Pubblicazione: (2024)

Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector
di: Wang, Hongbo, et al.
Pubblicazione: (2024)

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
di: Halloran, John T., et al.
Pubblicazione: (2026)

Take its Essence, Discard its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect
di: Lu, Junyu, et al.
Pubblicazione: (2024)

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement
di: Lu, Junyu, et al.
Pubblicazione: (2025)

Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites
di: Wang, Xintong, et al.
Pubblicazione: (2025)

STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection
di: Bai, Zewen, et al.
Pubblicazione: (2025)

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity
di: Lee, Yejin, et al.
Pubblicazione: (2025)

The Role of Information Incompleteness in Defending Against Stealth Attacks
di: Sun, Ke, et al.
Pubblicazione: (2025)

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
di: Cao, Bochuan, et al.
Pubblicazione: (2023)

Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarios
di: Tan, Bryan Chen Zhengyu, et al.
Pubblicazione: (2025)

Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes
di: Wang, Weiming, et al.
Pubblicazione: (2026)

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
di: Ge, Ziyu, et al.
Pubblicazione: (2025)

PclGPT: A Large Language Model for Patronizing and Condescending Language Detection
di: Wang, Hongbo, et al.
Pubblicazione: (2024)

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
di: Hu, Yujia, et al.
Pubblicazione: (2025)

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
di: Guo, Ping, et al.
Pubblicazione: (2024)

On Feasibility of Intent Obfuscating Attacks
di: Li, Zhaobin, et al.
Pubblicazione: (2024)

Unveiling the Impact of Multimodal Features on Chinese Spelling Correction: From Analysis to Design
di: Zhang, Xiaowu, et al.
Pubblicazione: (2025)

Essentials in communication [] / Kong zi xue yuan zong bu
di: Kong zi xue yuan zong bu
Pubblicazione: (2000)

Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
di: Hu, Qiang, et al.
Pubblicazione: (2024)

Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression
di: Wong, Zheng Jie, et al.
Pubblicazione: (2025)

The Harder You Try, The Harder You Fail: The KeyTrap Denial-of-Service Algorithmic Complexity Attacks on DNSSEC
di: Heftrig, Elias, et al.
Pubblicazione: (2024)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
di: Jin, Haotian, et al.
Pubblicazione: (2025)

Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation
di: Zhang, Bo, et al.
Pubblicazione: (2024)

Disassembling Obfuscated Executables with LLM
di: Rong, Huanyao, et al.
Pubblicazione: (2024)

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification
di: Li, Yu, et al.
Pubblicazione: (2025)

PhantomFetch: Obfuscating Loads against Prefetcher Side-Channel Attacks
di: Zhang, Xingzhi, et al.
Pubblicazione: (2025)

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks
di: Lee, Hanyong, et al.
Pubblicazione: (2025)

Defending against Backdoor Attacks via Module Switching
di: Li, Weijun, et al.
Pubblicazione: (2025)

Defending LLMs against Jailbreaking Attacks via Backtranslation
di: Wang, Yihan, et al.
Pubblicazione: (2024)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
di: Chew, Oscar, et al.
Pubblicazione: (2024)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
di: Zhou, Andy, et al.
Pubblicazione: (2024)

Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
di: Liu, Junhua, et al.
Pubblicazione: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
di: Xu, Zhangchen, et al.
Pubblicazione: (2024)

LifeTox: Unveiling Implicit Toxicity in Life Advice
di: Kim, Minbeom, et al.
Pubblicazione: (2023)

Integrating Multi-view Analysis: Multi-view Mixture-of-Expert for Textual Personality Detection
di: Zhu, Haohao, et al.
Pubblicazione: (2024)

ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations
di: Xiao, Yunze, et al.
Pubblicazione: (2024)

TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement
di: Lin, Zhiwei, et al.
Pubblicazione: (2024)

Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
di: Ma, Xuchen, et al.
Pubblicazione: (2025)

Defending against Backdoor Attack on Deep Neural Networks
di: Cheng, Hao, et al.
Pubblicazione: (2020)