When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Shiyao, Feng, Xijia, Wang, Yingkang, Yang, Junxiao, Zhang, Zhexin, Sikdar, Biplab, Wang, Hongning, Qiu, Han, Huang, Minlie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
by: Yang, Junxiao, et al.
Published: (2025)

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
by: Zhang, Zhexin, et al.
Published: (2025)

Agent-SafetyBench: Evaluating the Safety of LLM Agents
by: Zhang, Zhexin, et al.
Published: (2024)

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
by: Cui, Shiyao, et al.
Published: (2025)

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
by: Zhang, Zhexin, et al.
Published: (2025)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
by: Zhang, Zhexin, et al.
Published: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
by: Zhang, Zhexin, et al.
Published: (2023)

The Superalignment of Superhuman Intelligence with Large Language Models
by: Huang, Minlie, et al.
Published: (2024)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
by: Yang, Junxiao, et al.
Published: (2026)

The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
by: Zhang, Zhexin, et al.
Published: (2026)

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
by: Yang, Junxiao, et al.
Published: (2025)

LongSafety: Evaluating Long-Context Safety of Large Language Models
by: Lu, Yida, et al.
Published: (2025)

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
by: Yang, Shujian, et al.
Published: (2025)

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
by: Chen, Renmiao, et al.
Published: (2025)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
by: Tu, Jinzhe, et al.
Published: (2026)

The Effects of Emoji in Social Media Food Content: How Smileys, Hearts, and Hamburgers Affect Engagement, Attitudes, and Intentions
by: Lieke Verheijen, et al.
Published: (2025)

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
by: Zhang, Zhexin, et al.
Published: (2025)

Language Model Decoding as Direct Metrics Optimization
by: Ji, Haozhe, et al.
Published: (2023)

Grounding LLMs in Scientific Discovery via Embodied Actions
by: Zhang, Bo, et al.
Published: (2026)

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
by: Zhang, Zhexin, et al.
Published: (2024)

LiteAtt: A Peer-to-Peer Self-Attestation Framework and Handshake Protocol for Connected IoT Devices
by: Kohli, Varun, et al.
Published: (2026)

PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing
by: Kohli, Bhavya, et al.
Published: (2026)

From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs
by: Jain, Navya, et al.
Published: (2024)

Trust-Region Adaptive Policy Optimization
by: Su, Mingyu, et al.
Published: (2025)

Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
by: Wen, Jiaxin, et al.
Published: (2024)

FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
by: Cui, Shiyao, et al.
Published: (2023)

When In‐Groups Turn Hostile: Criminal Record, Intergroup Bias, and the Black Sheep Effect in Eyewitness Judgments
by: Nir Rozmann
Published: (2026)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
by: Feng, Andrew Zhuoer, et al.
Published: (2026)

Privacy-Preserving Collaborative Split Learning Framework for Smart Grid Load Forecasting
by: Iqbal, Asif, et al.
Published: (2024)

Learning Task Decomposition to Assist Humans in Competitive Programming
by: Wen, Jiaxin, et al.
Published: (2024)

AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
by: Guan, Jian, et al.
Published: (2024)

In-Memory Sorting-Searching with Cayley Tree
by: Paul, Subrata, et al.
Published: (2025)

When the Air Turns Toxic, So Might Our Behavior
by: Vạc Hoa
Published: (2025)

Think Socially via Cognitive Reasoning
by: Zhou, Jinfeng, et al.
Published: (2025)

UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
by: Han, Yuning, et al.
Published: (2024)

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
by: Chen, Renmiao, et al.
Published: (2026)

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework
by: Zhang, Xuanming, et al.
Published: (2024)

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs
by: Lu, Yiyang, et al.
Published: (2026)

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
by: Dongre, Vardhan, et al.
Published: (2026)

Unified Framework for Qualifying Security Boundary of PUFs Against Machine Learning Attacks
by: Fei, Hongming, et al.
Published: (2026)