FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design

Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficiency of existing training paradigms for reasoning enhancement. To address these issues, we propose an integrated framework, FinLMM-R1, combining an automated and scalable pipeline for data construction with enhanced training strategies to improve the multimodal reasoning of LMM. The Automated and Scalable Pipeline (ASP) resolves textual-visual misalignment in financial reports through a separate paradigm of question-answer generation and image-question alignment, ensuring data integrity and extraction efficiency. Through ASP, we collect 89,378 aligned image-question pairs from 23,397 financial reports, covering tasks such as arithmetic reasoning, statistics reasoning, financial explanation, and financial knowledge. Moreover, we introduce the Thinking with Adversarial Reward in LMM (TAR-LMM), extending the prior two-stage training framework [1] with additional reward mechanisms. In the first stage, we focus on text-only tasks with format and accuracy rewards to guide the model in generating well-structured thinking contents. In the second stage, we construct multi-image contrastive samples with additional reward components including image selection, thinking content length, and adversarial reward to jointly optimize the LMM across visual perception, reasoning efficiency, and logical coherence. Extensive experiments on 7 benchmarks show ASP-derived dataset and training framework significantly improve answer accuracy and reasoning depth over existing reasoning LMMs in both general and financial multimodal contexts.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks

Text-attributed graphs (TAGs) integrate textual data with graph structures, providing valuable insights in applications such as social network analysis and recommendation systems. Graph Neural Networks (GNNs) effectively capture both topological structure and textual information in TAGs but are vulnerable to adversarial attacks. Existing graph injection attack (GIA) methods assume that attackers can directly manipulate the embedding layer, producing non-explainable node embeddings. Furthermore, the effectiveness of these attacks often relies on surrogate models with high training costs. Thus, this paper introduces ATAG-LLM, a novel black-box GIA framework tailored for TAGs. Our approach leverages large language models (LLMs) to generate interpretable text-level node attributes directly, ensuring attacks remain feasible in real-world scenarios. We design strategies for LLM prompting that balance exploration and reliability to guide text generation, and propose a similarity assessment method to evaluate attack text effectiveness in disrupting graph homophily. This method efficiently perturbs the target node with minimal training costs in a strict black-box setting, ensuring a text-level graph injection attack for TAGs. Experiments on real-world TAG datasets validate the superior performance of ATAG-LLM compared to state-of-the-art embedding-level and text-level attack methods.

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable to adversarial attacks, particularly in the image modality, posing significant security concerns. Building upon our previous work on Adversarial Prompt Tuning (AdvPT), which introduced learnable text prompts to enhance adversarial robustness in VLMs without extensive parameter training, we present a significant extension by introducing the Neural Augmentor framework for Multi-modal Adversarial Prompt Tuning (NAP-Tuning).Our key innovations include: (1) extending AdvPT from text-only to multi-modal prompting across both text and visual modalities, (2) expanding from single-layer to multi-layer prompt architectures, and (3) proposing a novel architecture-level redesign through our Neural Augmentor approach, which implements feature purification to directly address the distortions introduced by adversarial attacks in feature space. Our NAP-Tuning approach incorporates token refiners that learn to reconstruct purified features through residual connections, allowing for modality-specific and layer-specific feature correction.Comprehensive experiments demonstrate that NAP-Tuning significantly outperforms existing methods across various datasets and attack types. Notably, our approach shows significant improvements over the strongest baselines under the challenging AutoAttack benchmark, outperforming them by 33.5% on ViT-B16 and 33.0% on ViT-B32 architectures while maintaining competitive clean accuracy.

Transforming Chatbot Text: A Sequence-to-Sequence Approach

Due to advances in Large Language Models (LLMs) such as ChatGPT, the boundary between human-written text and AI-generated text has become blurred. Nevertheless, recent work has demonstrated that it is possible to reliably detect GPT-generated text. In this paper, we adopt a novel strategy to adversarially transform GPT-generated text using sequence-to-sequence (Seq2Seq) models, with the goal of making the text more human-like. We experiment with the Seq2Seq models T5-small and BART which serve to modify GPT-generated sentences to include linguistic, structural, and semantic components that may be more typical of human-authored text. Experiments show that classification models trained to distinguish GPT-generated text are significantly less accurate when tested on text that has been modified by these Seq2Seq models. However, after retraining classification models on data generated by our Seq2Seq technique, the models are able to distinguish the transformed GPT-generated text from human-generated text with high accuracy. This work adds to the accumulating knowledge of text transformation as a tool for both attack -- in the sense of defeating classification models -- and defense -- in the sense of improved classifiers -- thereby advancing our understanding of AI-generated text.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing & Large-model Alignment Safety Grand Challenge (ATLAS) 2025}. This technical report presents findings from the competition, which involved 86 teams testing MLLM vulnerabilities via adversarial image-text attacks in two phases: white-box and black-box evaluations. The competition results highlight ongoing challenges in securing MLLMs and provide valuable guidance for developing stronger defense mechanisms. The challenge establishes new benchmarks for MLLM safety evaluation and lays groundwork for advancing safer multimodal AI systems. The code and data for this challenge are openly available at https://github.com/NY1024/ATLAS_Challenge_2025.

TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks

Inspired by the success of large language models (LLMs), there is a significant research shift from traditional graph learning methods to LLM-based graph frameworks, formally known as GraphLLMs. GraphLLMs leverage the reasoning power of LLMs by integrating three key components: the textual attributes of input nodes, the structural information of node neighborhoods, and task-specific prompts that guide decision-making. Despite their promise, the robustness of GraphLLMs against adversarial perturbations remains largely unexplored-a critical concern for deploying these models in high-stakes scenarios. To bridge the gap, we introduce TrustGLM, a comprehensive study evaluating the vulnerability of GraphLLMs to adversarial attacks across three dimensions: text, graph structure, and prompt manipulations. We implement state-of-the-art attack algorithms from each perspective to rigorously assess model resilience. Through extensive experiments on six benchmark datasets from diverse domains, our findings reveal that GraphLLMs are highly susceptible to text attacks that merely replace a few semantically similar words in a node's textual attribute. We also find that standard graph structure attack methods can significantly degrade model performance, while random shuffling of the candidate label set in prompt templates leads to substantial performance drops. Beyond characterizing these vulnerabilities, we investigate defense techniques tailored to each attack vector through data-augmented training and adversarial training, which show promising potential to enhance the robustness of GraphLLMs. We hope that our open-sourced library will facilitate rapid, equitable evaluation and inspire further innovative research in this field.

Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework

With the rapid advancements in deep learning, traditional CAPTCHA schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely on original image characteristics, resulting in distortions that hinder human interpretation and limit applicability in scenarios lacking initial input images. To address these challenges, we propose the Unsourced Adversarial CAPTCHA (UAC), a novel framework generating high-fidelity adversarial examples guided by attacker-specified text prompts. Leveraging a Large Language Model (LLM), UAC enhances CAPTCHA diversity and supports both targeted and untargeted attacks. For targeted attacks, the EDICT method optimizes dual latent variables in a diffusion model for superior image quality. In untargeted attacks, especially for black-box scenarios, we introduce bi-path unsourced adversarial CAPTCHA (BP-UAC), a two-step optimization strategy employing multimodal gradients and bi-path optimization for efficient misclassification. Experiments show BP-UAC achieves high attack success rates across diverse systems, generating natural CAPTCHAs indistinguishable to humans and DNNs.

Adversarial Text Generation with Dynamic Contextual Perturbation

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations, overlooking the broader context, which results in detectable or semantically inconsistent perturbations. We propose a novel adversarial text attack scheme named Dynamic Contextual Perturbation (DCP). DCP dynamically generates context-aware perturbations across sentences, paragraphs, and documents, ensuring semantic fidelity and fluency. Leveraging the capabilities of pre-trained language models, DCP iteratively refines perturbations through an adversarial objective function that balances the dual objectives of inducing model misclassification and preserving the naturalness of the text. This comprehensive approach allows DCP to produce more sophisticated and effective adversarial examples that better mimic natural language patterns. Our experimental results, conducted on various NLP models and datasets, demonstrate the efficacy of DCP in challenging the robustness of state-of-the-art NLP systems. By integrating dynamic contextual analysis, DCP significantly enhances the subtlety and impact of adversarial attacks. This study highlights the critical role of context in adversarial attacks and lays the groundwork for creating more robust NLP systems capable of withstanding sophisticated adversarial strategies.

AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches

Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world, revealing detectors' vulnerabilities and risks. However, these methods neglect the T2I patches' attack effectiveness when observed from different views in the physical world (i.e., angle robustness of the T2I adversarial patches). In this paper, we study the angle robustness of T2I adversarial patches comprehensively, revealing their angle-robust issues, demonstrating that texts affect the angle robustness of generated patches significantly, and task-specific linguistic instructions fail to enhance the angle robustness. Motivated by the studies, we introduce Angle-Robust Concept Learning (AngleRoCL), a simple and flexible approach that learns a generalizable concept (i.e., text embeddings in implementation) representing the capability of generating angle-robust patches. The learned concept can be incorporated into textual prompts and guides T2I models to generate patches with their attack effectiveness inherently resistant to viewpoint variations. Through extensive simulation and physical-world experiments on five SOTA detectors across multiple views, we demonstrate that AngleRoCL significantly enhances the angle robustness of T2I adversarial patches compared to baseline methods. Our patches maintain high attack success rates even under challenging viewing conditions, with over 50% average relative improvement in attack effectiveness across multiple angles. This research advances the understanding of physically angle-robust patches and provides insights into the relationship between textual concepts and physical properties in T2I-generated contents.

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation systems, underlying vulnerabilities can still be exploited by determined adversaries. Recent research on red-teaming and adversarial attacks against T2I models has notable limitations: some studies successfully generate highly toxic images but use adversarial prompts that are easily detected and blocked by safety filters, while others focus on bypassing safety mechanisms but fail to produce genuinely harmful outputs, neglecting the discovery of truly high-risk prompts. Consequently, there remains a lack of reliable tools for evaluating the safety of defended T2I models. To address this gap, we propose GenBreak, a framework that fine-tunes a red-team large language model (LLM) to systematically explore underlying vulnerabilities in T2I generators. Our approach combines supervised fine-tuning on curated datasets with reinforcement learning via interaction with a surrogate T2I model. By integrating multiple reward signals, we guide the LLM to craft adversarial prompts that enhance both evasion capability and image toxicity, while maintaining semantic coherence and diversity. These prompts demonstrate strong effectiveness in black-box attacks against commercial T2I generators, revealing practical and concerning safety weaknesses.