Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vulnerable to adversarial attacks—particularly adversarial patch attacks—which can pose serious threats in real-world scenarios. Existing patch-based attack methods are primarily designed for object detection models. Due to the more complex architectures and strong reasoning capabilities of MLLMs, these approaches perform poorly when transferred to MLLM-based systems. To address these limitations, we propose PhysPatch, a physically realizable and transferable adversarial patch framework tailored for MLLM-based AD systems. PhysPatch jointly optimizes patch location, shape, and content to enhance attack effectiveness and real-world applicability. It introduces a semantic-based mask initialization strategy for realistic placement, an SVD-based local alignment loss with patch-guided crop-resize to improve transferability, and a potential field-based mask refinement method. Extensive experiments across open-source, commercial, and reasoning-capable MLLMs demonstrate that PhysPatch significantly outperforms state-of-the-art (SOTA) methods in steering MLLM-based AD systems toward target-aligned perception and planning outputs. Moreover, PhysPatch consistently places adversarial patches in physically feasible regions of AD scenes, ensuring strong real-world applicability and deployability.

Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense, current methods are ill-suited for this scenario: they often perform poorly on high-resolution images and low perturbation budgets, and may introduce irrelevant semantic content. To address these limitations, we propose GeoShield, a novel adversarial framework designed for robust geoprivacy protection in real-world scenarios. GeoShield comprises three key modules: a feature disentanglement module that separates geographical and non-geographical information, an exposure element identification module that pinpoints geo-revealing regions within an image, and a scale-adaptive enhancement module that jointly optimizes perturbations at both global and local levels to ensure effectiveness across resolutions. Extensive experiments on challenging benchmarks show that GeoShield consistently surpasses prior methods in black-box settings, achieving strong privacy protection with minimal impact on visual or semantic quality. To our knowledge, this work is the first to explore adversarial perturbations for defending against geolocation inference by advanced VLMs, providing a practical solution to escalating privacy concerns.

Multimodal large reasoning models (MLRMs) have advanced visual-textual integration, enabling sophisticated human-AI interaction. While prior work has exposed MLRMs to visual jailbreaks, it remains underexplored how their reasoning capabilities reshape the security landscape under adversarial inputs. To fill this gap, we conduct a systematic security assessment of MLRMs and uncover a security-reasoning paradox: although deeper reasoning boosts cross‑modal risk recognition, it also creates cognitive blind spots that adversaries can exploit. We observe that MLRMs oriented toward human-centric service are highly susceptible to users' emotional cues during the deep-thinking stage, often overriding safety protocols or built‑in safety checks under high emotional intensity. Inspired by this key insight, we propose EmoAgent, an autonomous adversarial emotion-agent that orchestrates exaggerated affective prompts to hijack reasoning pathways. Even when visual risks are correctly identified, models can still produce harmful completions through emotional misalignment. We further identify persistent high-risk failure modes in transparent deep-thinking scenarios, such as MLRMs generating harmful reasoning masked behind seemingly safe responses. These failures expose misalignments between internal inference and surface-level behavior, eluding existing content-based safeguards. To quantify these risks, we introduce three metrics: (1) Risk-Reasoning Stealth Score (RRSS) for harmful reasoning beneath benign outputs; (2) Risk-Visual Neglect Rate (RVNR) for unsafe completions despite visual risk recognition; and (3) Refusal Attitude Inconsistency (RAIC) for evaluating refusal unstability under prompt variants. Extensive experiments on advanced MLRMs demonstrate the effectiveness of EmoAgent and reveal deeper emotional cognitive misalignments in model safety.

Large language model (LLM)-driven agents are designed to handle a wide range of tasks autonomously. As tasks become increasingly composite, the integration of multiple agents into a graph-structured system offers a promising solution. Recent advances mainly architect the communication order among agents into a specified directed acyclic graph, from which a one-by-one execution can be determined by topological sort. However, sequential architectures restrict the diversity of the information flow, hinder parallel computation, and exhibit vulnerabilities to potential backdoor threats. To overcome underlying shortcomings of sequential structures, we propose a node-wise multi-agent scheme, named message passing agent system (MPAS). Specifically, to parallelize the communication across agents, we extend the message propagation mechanism in graph representation learning to multi-agent scenarios and introduce our individual-epistemic message propagation. To further enhance expressiveness and robustness, we investigate three self-driven message aggregators. To achieve desired working flows, collaborative connections can be optimized without constraints. The experimental results reveal that compared to state-of-the-art sequential designs, MPAS could architect more advanced algorithms in 93.8% of the evaluations, reduce the average communication time from 84.6 seconds to 14.2 seconds per round on AQuA, and improve resilience against backdoor misinformation injection in 94.4% tests.

Multimodal large language models (MLLMs) have achieved significant advancements in multimodal understanding, reasoning, and interaction. However, they still suffer from hallucination, where the generated text often deviates from the factual content of the input image. To mitigate this issue, prior studies have primarily employed direct preference optimization (DPO) for human preference alignment. However, these approaches treat all textual words equally, neglecting the varying significance of individual words in grounding text generation to image content. This limitation hinders fine-grained semantic alignment and consequently constrains their effectiveness in hallucination suppression. To address this limitation, we propose a vision-guided lexical DPO method, called VGL-DPO. Specifically, we quantify the significance of words in positive preference data based on their relevance to the visual input and dynamically assign different weights to different words during training. This facilitates more precise optimization by emphasizing critical words that contribute to factual grounding. Additionally, we leverage the importance differences between high-significance words in positive and negative preference data to adaptively adjust the weight of the negative preference loss. This dynamic reweighting mechanism further refines the model’s ability to suppress hallucinated content while reinforcing factual accuracy. Extensive experiments across various models demonstrate that our method outperforms existing state-of-the-art methods in reducing hallucination and enhancing factual accuracy.

Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features—such as CLIP’s [CLS] token—between adversarial and target samples, they often overlook the rich local information encoded in patch tokens. This leads to suboptimal alignment and limited transferability, particularly for closed-source models. To address this limitation, we propose a targeted transferable adversarial attack method based on feature optimal alignment, called FOA-Attack, to improve adversarial transfer capability. Specifically, at the global level, we introduce a global feature loss based on cosine similarity to align the coarse-grained features of adversarial samples with those of target samples. At the local level, given the rich local representations within Transformers, we leverage clustering techniques to extract compact local patterns to alleviate redundant local features. We then formulate local feature alignment between adversarial and target samples as an optimal transport (OT) problem and propose a local clustering optimal transport loss to refine fine-grained feature alignment. Additionally, we propose a dynamic ensemble model weighting strategy to adaptively balance the influence of multiple models during adversarial example generation, thereby further improving transferability. Extensive experiments across various models demonstrate the superiority of the proposed method, outperforming state-of-the-art methods, especially in transferring to closed-source MLLMs.

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply aggressive filtering, leading to unnecessary loss of valuable information and reduced reliability in generation. To address this problem, we propose a two-stage semantic filtering and conflict-free framework for trustworthy RAG. In the first stage, we perform a joint filter with semantic and cluster-based filtering which is guided by the Entity-intent-relation extractor (EIRE). EIRE extracts entities, latent objectives, and entity relations from both the user query and filtered documents, scores their semantic relevance, and selectively adds valuable documents into the clean retrieval database. In the second stage, we proposed an EIRE-guided conflict-aware filtering module, which analyzes semantic consistency between the query, candidate answers, and retrieved knowledge before final answer generation, filtering out internal and external contradictions that could mislead the model. Through this two-stage process, SeCon-RAG effectively preserves useful knowledge while mitigating conflict contamination, achieving significant improvements in both generation robustness and output trustworthiness. Extensive experiments across various LLMs and datasets demonstrate that the proposed SeCon-RAG markedly outperforms state-of-the-art defense methods.

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to developing more robust and practical VLP models. Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process, aiming to improve transferability by expanding the contrast space of image-text features. However, these methods focus solely on diversity around the current AEs, yielding limited gains in transferability. To address this issue, we propose to increase the diversity of AEs by leveraging the intersection regions along the adversarial trajectory during optimization. Specifically, we propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity. We provide a theoretical analysis to demonstrate the effectiveness of the proposed adversarial evolution triangle. Moreover, we find that redundant inactive dimensions can dominate similarity calculations, distorting feature matching and making AEs model-dependent with reduced transferability. Hence, we propose to generate AEs in the semantic image-text feature contrast space, which can project the original feature space into a semantic corpus subspace. The proposed semantic-aligned subspace can reduce the image feature redundancy, thereby improving adversarial transferability. Extensive experiments across different datasets and models demonstrate that the proposed method can effectively improve adversarial transferability and outperform state-of-the-art adversarial attack methods.

Using deep neural networks to detect fake news has gradually become an extremely important field of research. Recent studies, which adopt fine-tuning BERT to detect fake news, have yielded promising results. Unfortunately, fine-tuning BERT is prone to overfitting the training data , which may reduce its generalization ability . The problem remains challenging when one tries to generalize the detector to unseen fake news. First, we investigate the effects of several fine-tuning strategies on the generalization of BERT models used in fake news detection. Specifically, we explore three fine-tuning strategies, which include initialization of model parameters, freezing of model parameters, and training iterations for fine-tuning. Besides, we propose an adversarial fine-tuning strategy to boost the generalization of fine-tuning BERT for fake news detection. In detail, we define the BERT fine-tuning procedure as a mini-max optimization problem . We also propose a novel adversarial fine-tuning training strategy based on feature regularization , called FGM-FRAT, to further improve the generalization. Specifically, we propose to adopt the model representation to guide the generation of adversarial examples during adversarial training on the word vector space. The proposed method outperforms state-of-the-art fake news detection methods. Extensive experiments on several benchmark databases, which include FakeNewsNet, BuzzFeedNews, LIAR, WELFake, and KaggleFakeNews, show that using the proposed method improves the generalization accuracy from 61% to 73% for BERT. It indicates that our FGM-FRAT can greatly improve the generalization of fine-tuning BERT for fake news detection. Moreover, the proposed method also can be extended to other pre-trained language models and other text classification tasks .