Cover Image

All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Ziyou, Li, Mingyang, Wang, Junjie, Huang, Yuekai, Huang, Jie, Chang, Zhiyuan, Li, Zhaoyang, Wang, Qing
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
by: Wang, Wenshuo, et al.
Published: (2025)

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
by: Jiang, Ziyou, et al.
Published: (2025)

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
by: Chang, Zhiyuan, et al.
Published: (2026)

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
by: Chang, Zhiyuan, et al.
Published: (2025)

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
by: Xiong, Qian, et al.
Published: (2025)

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
by: Chang, Zhiyuan, et al.
Published: (2024)

Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectories
by: Xiong, Qian, et al.
Published: (2026)

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
by: Wang, Haowei, et al.
Published: (2024)

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
by: Wang, Haowei, et al.
Published: (2025)

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
by: Chang, Zhiyuan, et al.
Published: (2024)

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
by: Zheng, Yujia, et al.
Published: (2025)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
by: Chang, Zhiyuan, et al.
Published: (2024)

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
by: Chang, Zhiyuan, et al.
Published: (2024)

Where Have All the Records Gone, or When Will We Ever Learn?
by: Burns, Gary
Published: (1993)

VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
by: Jiang, Ziyou, et al.
Published: (2025)

Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
by: Chang, Zhiyuan, et al.
Published: (2024)

Constant in an Ever-Changing World
by: Wu, Andy, et al.
Published: (2025)

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

Towards Low-Resource Harmful Meme Detection with LMM Agents
by: Huang, Jianzhao, et al.
Published: (2024)

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

MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
by: Gu, Hexiang, et al.
Published: (2025)

Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains
by: Qin, Hao, et al.
Published: (2024)

OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst
by: Cao, Jingtao, et al.
Published: (2024)

Invariant measures and their limiting behavior of the Landau-Lifshitz-Bloch equation in unbounded domains
by: Huang, Daiwen, et al.
Published: (2024)

Will Schooling Ever Change?
by: Mikiewicz, Piotr, et al.
Published: (2023)

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

PRNet: Original Information Is All You Have
by: Zheng, PeiHuang, et al.
Published: (2025)

Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Content
by: Tong, Ran, et al.
Published: (2025)

MemeCMD: An Automatically Generated Chinese Multi-turn Dialogue Dataset with Contextually Retrieved Memes
by: Wang, Yuheng, et al.
Published: (2025)

A Roadmap for Software Testing in Open Collaborative Development Environments
by: Wang, Qing, et al.
Published: (2024)

MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal
by: Nie, Yiqi, et al.
Published: (2026)

Continuations: What Have They Ever Done for Us? (Experience Report)
by: Kaufmann, Marc, et al.
Published: (2024)

Unblind Text Inputs: Predicting Hint-text of Text Input in Mobile Apps via LLM
by: Liu, Zhe, et al.
Published: (2024)

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

RAM: Towards an Ever-Improving Memory System by Learning from Communications
by: Li, Jiaqi, et al.
Published: (2024)

Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs
by: Yang, Chang, et al.
Published: (2025)

All the experimental validation data for the manuscript "Spatial transcriptomics elucidates the central role of cerebral vasculatures in the progression of Japanese encephalitis"
by: Wang, Zhaoyang, et al.
Published: (2026)

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

A Template Is All You Meme
by: Bates, Luke, et al.
Published: (2023)

Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
by: Yang, Jinluan, et al.
Published: (2024)