More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection

• URL: http://arxiv.org/abs/2603.21298v1
• Date: Sun, 22 Mar 2026 15:46:23 GMT
• Title: More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection
• Abstract summary: Hate speech on social media is critical for securing cyberspace, yet relies heavily on automated detection systems.<n>We characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion.<n>We propose the Asymmetric Reasoning via Courtroom Agent DEbate framework to effectively decipher these complex cues.
• Score: 49.07221734365168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As content formats evolve, hate speech is transitioning from solely plain text to complex multimodal expressions, making implicit attacks harder to spot. Current systems, however, often falter on these subtle cases, as they struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. To bridge this gap, we move beyond binary classification to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. Guided by this fine-grained formulation, we curate the Hate via Vision-Language Interplay (H-VLI) benchmark where the true intent hinges on the intricate interplay of modalities rather than overt visual or textual slurs. To effectively decipher these complex cues, we further propose the Asymmetric Reasoning via Courtroom Agent DEbate (ARCADE) framework. By simulating a judicial process where agents actively argue for accusation and defense, ARCADE forces the model to scrutinize deep semantic cues before reaching a verdict. Extensive experiments demonstrate that ARCADE significantly outperforms state-of-the-art baselines on H-VLI, particularly for challenging implicit cases, while maintaining competitive performance on established benchmarks. Our code and data are available at: https://github.com/Sayur1n/H-VLI

Related papers

• Robust Context-Aware Detection of Malicious Instructions in Text [22.27527497326564]
  A fundamental task in addressing this vulnerability is successful segmentation of a given text into benign and malicious sentences.<n>We develop an approach for malicious sentence classification that is both context- and query-aware.<n>We show that the proposed approach outperforms state-of-the-art IPI defense baselines under static attacks.
  arXiv  Detail & Related papers  (2026-08-05T21:44:44Z)
• Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction [67.45032003041399]
  We propose a Semantic-Augmented Dynamic Contrastive Attack (SADCA) that enhances adversarial transferability through progressive and semantically guided perturbations.<n>SADCA establishes a contrastive learning mechanism involving adversarial, positive and negative samples, to reinforce the semantic inconsistency of the obtained perturbations.<n>Experiments on multiple datasets and models demonstrate that SADCA significantly improves adversarial transferability and consistently surpasses state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-05T05:46:16Z)
• TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech [11.020614074201346]
  We introduce TANDEM, a unified framework that transforms audio-visual hate detection into a structured reasoning problem.<n>Our approach employs a novel tandem reinforcement learning strategy where vision-language and audio-language models optimize each other.<n>TANDEM significantly outperforms zero-shot and context-augmented baselines, achieving 0.73 F1 in target identification on HateMM.
  arXiv  Detail & Related papers  (2026-01-16T10:52:12Z)
• DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection [6.225860651499494]
  Multimodal fake news detection is crucial for mitigating adversarial misinformation.<n>We propose DIVER (Dynamic Iterative Visual Evidence Reasoning), a framework grounded in a progressive, evidence-driven reasoning paradigm.<n>Experiments on Weibo, Weibo21, and GossipCop demonstrate that DIVER outperforms state-of-the-art baselines by an average of 2.72%.
  arXiv  Detail & Related papers  (2026-01-12T04:01:33Z)
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation [60.63465682731118]
  The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity.<n>We introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks.<n>Our framework improves the intent clarification performance of small language models by approximately 30%, making them competitive with significantly larger counterparts.
  arXiv  Detail & Related papers  (2025-11-12T04:28:14Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance [10.105673138616483]
  Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents.<n>As attackers evolve with paraphrased, obfuscated, and even multi-task injection strategies, existing benchmarks are no longer sufficient to capture the full spectrum of emerging threats.<n>We propose PromptSleuth, a semantic-oriented defense framework that detects prompt injection by reasoning over task-level intent rather than surface features.
  arXiv  Detail & Related papers  (2025-08-28T15:19:07Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement [14.437386966111719]
  This study presents HATE WATCH, a novel framework of weakly supervised causal disentanglement. It circumvents the need for explicit target labeling and effectively disentangles input features into invariant representations of hate. Empirical validation across platforms two with target labels and two without positions HATE WATCH as a novel method in cross platform hate speech detection with superior performance.
  arXiv  Detail & Related papers  (2024-04-17T03:25:54Z)
• Few-Shot Adversarial Prompt Learning on Vision-Language Models [62.50622628004134]
  The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Previous efforts achieved zero-shot adversarial robustness by aligning adversarial visual features with text supervision. We propose a few-shot adversarial prompt framework where adapting input sequences with limited data makes significant adversarial robustness improvement.
  arXiv  Detail & Related papers  (2024-03-21T18:28:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.