Imagen de Portada

HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Zhu, Shenzhe
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
por: Huang, Tiansheng, et al.
Publicado: (2024)

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
por: Yang, Langqi, et al.
Publicado: (2025)

Self-HarmLLM: Can Large Language Model Harm Itself?
por: Kim, Heehwan, et al.
Publicado: (2025)

Human-Guided Harm Recovery for Computer Use Agents
por: Li, Christy, et al.
Publicado: (2026)

Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor
por: Sharshar, Ahmed, et al.
Publicado: (2026)

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
por: Lin, Hongzhan, et al.
Publicado: (2024)

PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
por: Li, Jing-Jing, et al.
Publicado: (2026)

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

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts
por: Schoene, Annika M, et al.
Publicado: (2025)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
por: Pandey, Punya Syon, et al.
Publicado: (2025)

REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM
por: Jindal, Madhur, et al.
Publicado: (2025)

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
por: Jeung, Wonje, et al.
Publicado: (2025)

When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Attribution
por: Nian, Yi, et al.
Publicado: (2026)

MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection
por: Liu, Ziyan, et al.
Publicado: (2025)

FairBelief -- Assessing Harmful Beliefs in Language Models
por: Setzu, Mattia, et al.
Publicado: (2024)

More of the Same: Persistent Representational Harms Under Increased Representation
por: Mickel, Jennifer, et al.
Publicado: (2025)

HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment
por: Mekky, Ali, et al.
Publicado: (2025)

Beyond Accuracy: An Explainability-Driven Analysis of Harmful Content Detection
por: Dhara, Trishita, et al.
Publicado: (2026)

Harmful Suicide Content Detection
por: Park, Kyumin, et al.
Publicado: (2024)

Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation
por: Lee, Huije, et al.
Publicado: (2026)

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
por: Lu, Guoxin, et al.
Publicado: (2026)

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
por: Joo, Seongho, et al.
Publicado: (2025)

ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information
por: Hui, Zheng, et al.
Publicado: (2024)

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
por: Qu, Jiaming, et al.
Publicado: (2026)

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
por: Liu, Kangwei, et al.
Publicado: (2025)

Weighted Grouped Query Attention in Transformers
por: Chinnakonduru, Sai Sena, et al.
Publicado: (2024)

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
por: Wang, Yibo, et al.
Publicado: (2025)

Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
por: Shukla, Vaibhav, et al.
Publicado: (2026)

Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
por: Bianchi, Federico, et al.
Publicado: (2024)

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion
por: Liu, Tongxuan, et al.
Publicado: (2024)

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
por: Chen, Zixin, et al.
Publicado: (2025)

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments
por: Muminovic, Amel
Publicado: (2025)

VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
por: Sun, Qixin, et al.
Publicado: (2025)

Combating Adversarial Attacks with Multi-Agent Debate
por: Chern, Steffi, et al.
Publicado: (2024)

Dynamic Role Assignment for Multi-Agent Debate
por: Zhang, Miao, et al.
Publicado: (2026)

KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection
por: Li, Yaocong, et al.
Publicado: (2026)

Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
por: Sicilia, Anthony, et al.
Publicado: (2024)

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
por: Jones, Jaylen, et al.
Publicado: (2026)

Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
por: Wang, Haotian, et al.
Publicado: (2023)