Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization

Ensuring the safety of generated content remains a fundamental challenge for Text-to-Image (T2I) generation. Existing studies either fail to guarantee complete safety under potentially harmful concepts or struggle to balance safety with generation quality. To address these issues, we propose Safety-Constrained Direct Preference Optimization (SC-DPO), a novel framework for safety alignment in T2I models. SC-DPO integrates safety constraints into the general human preference calibration, aiming to maximize the likelihood of generating human-preferred samples while minimizing the safety cost of the generated outputs. In SC-DPO, we introduce a safety cost model to accurately quantify harmful levels for images, and train it effectively using the proposed contrastive learning and cost anchoring objectives. To apply SC-DPO for effective T2I safety alignment, we constructed SCP-10K, a safety-constrained preference dataset containing rich harmful concepts, which blends safety-constrained preference pairs under both harmful and clean instructions, further mitigating the trade-off between safety and sample quality. Additionally, we propose a Dynamic Focusing Mechanism (DFM) for SC-DPO, promoting the model's learning of difficult preference pair samples. Extensive experiments demonstrate that SC-DPO outperforms existing methods, effectively defending against various NSFW content while maintaining optimal sample quality and human preference alignment. Additionally, SC-DPO exhibits resilience against adversarial prompts designed to generate harmful content.

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability

Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematics and coding. However, the open-source R1 models have raised safety concerns in wide applications, such as the tendency to comply with malicious queries, which greatly impacts the utility of these powerful models in their applications. In this paper, we introduce RealSafe-R1 as safety-aligned versions of DeepSeek-R1 distilled models. To train these models, we construct a dataset of 15k safety-aware reasoning trajectories generated by DeepSeek-R1, under explicit instructions for expected refusal behavior. Both quantitative experiments and qualitative case studies demonstrate the models' improvements, which are shown in their safety guardrails against both harmful queries and jailbreak attacks. Importantly, unlike prior safety alignment efforts that often compromise reasoning performance, our method preserves the models' reasoning capabilities by maintaining the training data within the original distribution of generation. Model weights of RealSafe-R1 are open-source at https://huggingface.co/RealSafe.

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Vision-Language Models (VLMs) have achieved remarkable success in various tasks, yet their robustness to real-world illumination variations remains largely unexplored. To bridge this gap, we propose \textbf{I}llumination \textbf{T}ransformation \textbf{A}ttack (\textbf{ITA}), the first framework to systematically assess VLMs' robustness against illumination changes. However, there still exist two key challenges: (1) how to model global illumination with fine-grained control to achieve diverse lighting conditions and (2) how to ensure adversarial effectiveness while maintaining naturalness. To address the first challenge, we innovatively decompose global illumination into multiple parameterized point light sources based on the illumination rendering equation. This design enables us to model more diverse lighting variations that previous methods could not capture. Then, by integrating these parameterized lighting variations with physics-based lighting reconstruction techniques, we could precisely render such light interactions in the original scenes, finally meeting the goal of fine-grained lighting control. For the second challenge, by controlling illumination through the lighting reconstrution model's latent space rather than direct pixel manipulation, we inherently preserve physical lighting priors. Furthermore, to prevent potential reconstruction artifacts, we design additional perceptual constraints for maintaining visual consistency with original images and diversity constraints for avoiding light source convergence. Extensive experiments demonstrate that our ITA could significantly reduce the performance of advanced VLMs, e.g., LLaVA-1.6, while possessing competitive naturalness, exposing VLMS' critical illuminiation vulnerabilities.

STAIR: Improving Safety Alignment with Introspective Reasoning

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the susceptibility to jailbreak attacks, primarily due to their reliance on direct refusals for malicious queries. In this paper, we propose STAIR, a novel framework that integrates SafeTy Alignment with Itrospective Reasoning. We enable LLMs to identify safety risks through step-by-step analysis by self-improving chain-of-thought (CoT) reasoning with safety awareness. STAIR first equips the model with a structured reasoning capability and then advances safety alignment via iterative preference optimization on step-level reasoning data generated using our newly proposed Safety-Informed Monte Carlo Tree Search (SI-MCTS). We further train a process reward model on this data to guide test-time searches for improved responses. Extensive experiments show that STAIR effectively mitigates harmful outputs while better preserving helpfulness, compared to instinctive alignment strategies. With test-time scaling, STAIR achieves a safety performance comparable to Claude-3.5 against popular jailbreak attacks. Relevant resources in this work are available at https://github.com/thu-ml/STAIR.

PaMMA-Net: Plasmas magnetic measurement evolution based on data-driven incremental accumulative prediction

An accurate evolution model is crucial for effective control and in-depth study of fusion plasmas. Evolution methods based on physical models often encounter challenges such as insufficient robustness or excessive computational costs. Given the proven strong fitting capabilities of deep learning methods across various fields, including plasma research, this paper introduces a deep learning-based magnetic measurement evolution method named PaMMA-Net (Plasma Magnetic Measurements Incremental Accumulative Prediction Network). This network is capable of evolving magnetic measurements in tokamak discharge experiments over extended periods or, in conjunction with equilibrium reconstruction algorithms, evolving macroscopic parameters such as plasma shape. Leveraging a incremental prediction approach and data augmentation techniques tailored for magnetic measurements, PaMMA-Net achieves superior evolution results compared to existing studies. The tests conducted on real experimental data from EAST validate the high generalization capability of the proposed method.

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

Vision Language Models (VLMs) have exhibited remarkable generalization capabilities, yet their robustness in dynamic real-world scenarios remains largely unexplored. To systematically evaluate VLMs' robustness to real-world 3D variations, we propose AdvDreamer, the first framework that generates physically reproducible adversarial 3D transformation (Adv-3DT) samples from single-view images. AdvDreamer integrates advanced generative techniques with two key innovations and aims to characterize the worst-case distributions of 3D variations from natural images. To ensure adversarial effectiveness and method generality, we introduce an Inverse Semantic Probability Objective that executes adversarial optimization on fundamental vision-text alignment spaces, which can be generalizable across different VLM architectures and downstream tasks. To mitigate the distribution discrepancy between generated and real-world samples while maintaining physical reproducibility, we design a Naturalness Reward Model that provides regularization feedback during adversarial optimization, preventing convergence towards hallucinated and unnatural elements. Leveraging AdvDreamer, we establish MM3DTBench, the first VQA dataset for benchmarking VLMs' 3D variations robustness. Extensive evaluations on representative VLMs with diverse architectures highlight that 3D variations in the real world may pose severe threats to model performance across various tasks.

Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holistic evaluation to offer thorough insights into future improvements. In this work, we establish MultiTrust, the first comprehensive and unified benchmark on the trustworthiness of MLLMs across five primary aspects: truthfulness, safety, robustness, fairness, and privacy. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts, encompassing 32 diverse tasks with self-curated datasets. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks, highlighting the complexities introduced by the multimodality and underscoring the necessity for advanced methodologies to enhance their reliability. For instance, typical proprietary models still struggle with the perception of visually confusing images and are vulnerable to multimodal jailbreaking and adversarial attacks; MLLMs are more inclined to disclose privacy in text and reveal ideological and cultural biases even when paired with irrelevant images in inference, indicating that the multimodality amplifies the internal risks from base LLMs. Additionally, we release a scalable toolbox for standardized trustworthiness research, aiming to facilitate future advancements in this important field. Code and resources are publicly available at: https://multi-trust.github.io/.

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models

Vision-Language Pre-training (VLP) models like CLIP have achieved remarkable success in computer vision and particularly demonstrated superior robustness to distribution shifts of 2D images. However, their robustness under 3D viewpoint variations is still limited, which can hinder the development for real-world applications. This paper successfully addresses this concern while keeping VLPs' original performance by breaking through two primary obstacles: 1) the scarcity of training data and 2) the suboptimal fine-tuning paradigms. To combat data scarcity, we build the Multi-View Caption (MVCap) dataset -- a comprehensive collection of over four million multi-view image-text pairs across more than 100K objects, providing more potential for VLP models to develop generalizable viewpoint-invariant representations. To address the limitations of existing paradigms in performance trade-offs and training efficiency, we design a novel fine-tuning framework named Omniview-Tuning (OVT). Specifically, OVT introduces a Cross-Viewpoint Alignment objective through a minimax-like optimization strategy, which effectively aligns representations of identical objects from diverse viewpoints without causing overfitting. Additionally, OVT fine-tunes VLP models in a parameter-efficient manner, leading to minimal computational cost. Extensive experiments on various VLP models with different architectures validate that OVT significantly improves the models' resilience to viewpoint shifts and keeps the original performance, establishing a pioneering standard for boosting the viewpoint invariance of VLP models.

Embodied Adversarial Attack: A Dynamic Robust Physical Attack in Autonomous Driving

As physical adversarial attacks become extensively applied in unearthing the potential risk of security-critical scenarios, especially in autonomous driving, their vulnerability to environmental changes has also been brought to light. The non-robust nature of physical adversarial attack methods brings less-than-stable performance consequently. To enhance the robustness of physical adversarial attacks in the real world, instead of statically optimizing a robust adversarial example via an off-line training manner like the existing methods, this paper proposes a brand new robust adversarial attack framework: Embodied Adversarial Attack (EAA) from the perspective of dynamic adaptation, which aims to employ the paradigm of embodied intelligence: Perception-Decision-Control to dynamically adjust the optimal attack strategy according to the current situations in real time. For the perception module, given the challenge of needing simulation for the victim's viewpoint, EAA innovatively devises a Perspective Transformation Network to estimate the target's transformation from the attacker's perspective. For the decision and control module, EAA adopts the laser-a highly manipulable medium to implement physical attacks, and further trains an attack agent with reinforcement learning to make it capable of instantaneously determining the best attack strategy based on the perceived information. Finally, we apply our framework to the autonomous driving scenario. A variety of experiments verify the high effectiveness of our method under complex scenes.

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D adversarial samples, due to their potential of multi-view robustness, can more comprehensively identify weaknesses in existing deep learning systems, possessing great application value. However, the field of transferable targeted 3D adversarial attacks remains vacant. The goal of this work is to develop a more effective technique that could generate transferable targeted 3D adversarial examples, filling the gap in this field. To achieve this goal, we design a novel framework named TT3D that could rapidly reconstruct from few multi-view images into Transferable Targeted 3D textured meshes. While existing mesh-based texture optimization methods compute gradients in the high-dimensional mesh space and easily fall into local optima, leading to unsatisfactory transferability and distinct distortions, TT3D innovatively performs dual optimization towards both feature grid and Multi-layer Perceptron (MLP) parameters in the grid-based NeRF space, which significantly enhances black-box transferability while enjoying naturalness. Experimental results show that TT3D not only exhibits superior cross-model transferability but also maintains considerable adaptability across different renders and vision tasks. More importantly, we produce 3D adversarial examples with 3D printing techniques in the real world and verify their robust performance under various scenarios.