The proliferation of multimodal misinformation poses growing threats to public discourse and societal trust. While Large Vision-Language Models (LVLMs) have enabled recent progress in multimodal misinformation detection (MMD), the rise of generative AI (GenAI) tools introduces a new challenge: GenAI-driven news diversity, characterized by highly varied and complex content. We show that this diversity induces multi-level drift, comprising (1) model-level misperception drift, where stylistic variations disrupt a model’s internal reasoning, and (2) evidence-level drift, where expression diversity degrades the quality or relevance of retrieved external evidence. These drifts significantly degrade the robustness of current LVLM-based MMD systems. To systematically study this problem, we introduce DriftBench, a large-scale benchmark comprising 16,000 news instances across six categories of diversification. We design three evaluation tasks: (1) robustness of truth verification under multi-level drift; (2) susceptibility to adversarial evidence contamination generated by GenAI; and (3) analysis of reasoning consistency across diverse inputs. Experiments with six state-of-the-art LVLM-based detectors show substantial performance drops (average F1 ↓ 14.8%) and increasingly unstable reasoning traces, with even more severe failures under adversarial evidence injection. Our findings uncover fundamental vulnerabilities in existing MMD systems and suggest an urgent need for more resilient approaches in the GenAI era.

Tingchao Fu, Wenkai Wang, Fanxiao Li, Huadong Zhang, Jinhong Zhang, Dayang Li, Yunyun Dong, Renyang Liu, Wei Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports.This covert harm is subtler than explicit misinformation, yet remains underexplored.To address this gap, we develop a multistage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-MISLEADING benchmark.Using MM-MISLEADING, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection.We further propose OM-GUARD, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions.Experiments show that OM-GUARD lifts an 8B model's detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction.Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.

Jiaying Wu, Zihang Fu, Haonan Wang, Fanxiao Li, Jiafeng Guo, Preslav Nakov, Min-Yen Kan. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Dayang Li, Fanxiao Li, Bingbing Song, Li Tang, Wei Zhou. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Text steganography is a technique for hiding secret messages within texts. Previous approaches neglect the contextual relevance of generated stego texts (texts containing secrets) and consistently transmitted secret messages unidirectionally. This behavior is considered anomalous and thus arouses the suspicion of potential attackers. In this paper, we first propose a text steganography framework grounded in the group chat scenario named GCStego, aimed at enhancing the behavior imperceptibility. Additionally, we employ a large language model (LLM) to generate stego texts according to the chatting history and thus boosts the contextual relevance. The proposed scheme is well-suited for secret transmission in group chatting, where multiple agents can pass secret messages through stego texts like regular conversations. Furthermore, we propose token index-based encoding, position filtering and sentence split strategies to deliver the performance. Experimental results demonstrate the superiority of our proposed framework in terms of text semantic controllability, behavioral imperceptibility, and anti-steganalysis ability.

The robustness and security of deep neural network (DNN) models have received much attention in recent years. In-depth research on adversarial example generation methods that make DNN models make wrong judgments and decisions will facilitate further research on more comprehensive and practical adversarial defense methods. Most existing adversarial example generation methods focus too much on attack performance and design adversarial noise at the pixel level, resulting in the generated adversarial examples with redundant noise and evident perturbations. In this paper, we try to find the well-designed perturbations at the feature-level and propose a novel deep reversible network-based imperceptible adversarial examples generation method called RIA. Experimental results show that RIA can obtain more natural adversarial examples without losing attack performance and reducing redundant noise based on well-designed feature maps. To the best of our knowledge, in the white-box attack method research, this work is the first attempt to directly add perturbations to feature maps and use an reversible network to generate adversarial examples based on the perturbed feature maps.