Xiaojun Jia

Yihao Huang, Le Liang, Tianlin Li et al.

In recent years, Text-to-Image (T2I) models have garnered significant attention due to their remarkable advancements. However, security concerns have emerged due to their potential to generate inappropriate or Not-Safe-For-Work (NSFW) images. In this paper, inspired by the observation that texts with different semantics can lead to similar human perceptions, we propose an LLM-driven perception-guided jailbreak method, termed PGJ. It is a black-box jailbreak method that requires no specific T2I model (model-free) and generates highly natural attack prompts. Specifically, we propose identifying a safe phrase that is similar in human perception yet inconsistent in text semantics with the target unsafe word and using it as a substitution. The experiments conducted on six open-source models and commercial online services with thousands of prompts have verified the effectiveness of PGJ.

Xiaojun Jia, Sensen Gao, Simeng Qin et al.

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. The code is released at https://github.com/jiaxiaojunQAQ/FOA-Attack.

Xiaojun Jia, Sensen Gao, Qing Guo et al.

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. The code is released at https://github.com/jiaxiaojunQAQ/SA-AET.

Yihao Huang, Chong Wang, Xiaojun Jia et al.

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and time-consuming. Also, they have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt. To this end, we propose a method called POUGH that incorporates an efficient optimization algorithm and two semantics-guided prompt organization strategies. Specifically, our method starts with a sampling strategy to select representative prompts from a candidate pool, followed by a ranking strategy that prioritizes them. Given the sequentially ranked prompts, our method employs an iterative optimization algorithm to generate a fixed suffix that can concatenate to arbitrary user prompts for universal goal hijacking. Experiments conducted on four popular LLMs and ten types of target responses verified the effectiveness.

Zhitao Zeng, Zhu Zhuo, Xiaojun Jia et al. · pku

Foundation models have achieved transformative success across biomedical domains by enabling holistic understanding of multimodal data. However, their application in surgery remains underexplored. Surgical intelligence presents unique challenges - requiring surgical visual perception, temporal analysis, and reasoning. Existing general-purpose vision-language models fail to address these needs due to insufficient domain-specific supervision and the lack of a large-scale high-quality surgical database. To bridge this gap, we propose SurgVLM, one of the first large vision-language foundation models for surgical intelligence, where this single universal model can tackle versatile surgical tasks. To enable this, we construct a large-scale multimodal surgical database, SurgVLM-DB, comprising over 1.81 million frames with 7.79 million conversations, spanning more than 16 surgical types and 18 anatomical structures. We unify and reorganize 23 public datasets across 10 surgical tasks, followed by standardizing labels and doing hierarchical vision-language alignment to facilitate comprehensive coverage of gradually finer-grained surgical tasks, from visual perception, temporal analysis, to high-level reasoning. Building upon this comprehensive dataset, we propose SurgVLM, which is built upon Qwen2.5-VL, and undergoes instruction tuning to 10+ surgical tasks. We further construct a surgical multimodal benchmark, SurgVLM-Bench, for method evaluation. SurgVLM-Bench consists of 6 popular and widely-used datasets in surgical domain, covering several crucial downstream tasks. Based on SurgVLM-Bench, we evaluate the performance of our SurgVLM (3 SurgVLM variants: SurgVLM-7B, SurgVLM-32B, and SurgVLM-72B), and conduct comprehensive comparisons with 14 mainstream commercial VLMs (e.g., GPT-4o, Gemini 2.0 Flash, Qwen2.5-Max).

Zhiyuan Chang, Mingyang Li, Xiaojun Jia et al.

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly accessible and modifiable. While previous studies have exposed knowledge poisoning risks in RAG systems, existing attack methods suffer from critical limitations: they either require injecting multiple poisoned documents (resulting in poor stealthiness) or can only function effectively on simplistic queries (limiting real-world applicability). This paper reveals a more realistic knowledge poisoning attack against RAG systems that achieves successful attacks by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. Our proposed AuthChain address three challenges to ensure the poisoned documents are reliably retrieved and trusted by the LLM, even against large knowledge bases and LLM's own knowledge. Extensive experiments across six popular LLMs demonstrate that AuthChain achieves significantly higher attack success rates while maintaining superior stealthiness against RAG defense mechanisms compared to state-of-the-art baselines.

Haoming Yang, Ke Ma, Xiaojun Jia et al.

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing to uncover potential risks in real-world scenarios. To address this, we propose a novel jailbreak attack framework, ICRT, inspired by heuristics and biases in human cognition. Leveraging the simplicity effect, we employ cognitive decomposition to reduce the complexity of malicious prompts. Simultaneously, relevance bias is utilized to reorganize prompts, enhancing semantic alignment and inducing harmful outputs effectively. Furthermore, we introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm by employing ranking aggregation methods such as Elo, HodgeRank, and Rank Centrality to comprehensively quantify the harmfulness of generated content. Experimental results show that our approach consistently bypasses mainstream LLMs' safety mechanisms and generates high-risk content, providing insights into jailbreak attack risks and contributing to stronger defense strategies.

Xinzhe Huang, Wenjing Hu, Tianhang Zheng et al.

Existing gradient-based jailbreak attacks on Large Language Models (LLMs), such as Greedy Coordinate Gradient (GCG) and COLD-Attack, typically optimize adversarial suffixes to align the LLM output with a predefined target response. However, by restricting the optimization objective as inducing a predefined target, these methods inherently constrain the adversarial search space, which limit their overall attack efficacy. Furthermore, existing methods typically require a large number of optimization iterations to fulfill the large gap between the fixed target and the original model response, resulting in low attack efficiency. To overcome the limitations of targeted jailbreak attacks, we propose the first gradient-based untargeted jailbreak attack (UJA), aiming to elicit an unsafe response without enforcing any predefined patterns. Specifically, we formulate an untargeted attack objective to maximize the unsafety probability of the LLM response, which can be quantified using a judge model. Since the objective is non-differentiable, we further decompose it into two differentiable sub-objectives for optimizing an optimal harmful response and the corresponding adversarial prompt, with a theoretical analysis to validate the decomposition. In contrast to targeted jailbreak attacks, UJA's unrestricted objective significantly expands the search space, enabling a more flexible and efficient exploration of LLM vulnerabilities.Extensive evaluations demonstrate that UJA can achieve over 80% attack success rates against recent safety-aligned LLMs with only 100 optimization iterations, outperforming the state-of-the-art gradient-based attacks such as I-GCG and COLD-Attack by over 20%.

Xinwei Liu, Xiaojun Jia, Yuan Xun et al.

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright infringement. To address these issues, researchers have proposed adversarial perturbation-based protection techniques. However, these methods have notable limitations, including insufficient robustness against data transformations and the inability to fully eliminate identifiable features of protected objects in the generated output. In this paper, we introduce PersGuard, a novel backdoor-based approach that prevents malicious personalization of specific images. Unlike traditional adversarial perturbation methods, PersGuard implant backdoor triggers into pre-trained T2I models, preventing the generation of customized outputs for designated protected images while allowing normal personalization for unprotected ones. Unfortunately, existing backdoor methods for T2I diffusion models fail to be applied to personalization scenarios due to the different backdoor objectives and the potential backdoor elimination during downstream fine-tuning processes. To address these, we propose three novel backdoor objectives specifically designed for personalization scenarios, coupled with backdoor retention loss engineered to resist downstream fine-tuning. These components are integrated into a unified optimization framework. Extensive experimental evaluations demonstrate PersGuard's effectiveness in preserving data privacy, even under challenging conditions including gray-box settings, multi-object protection, and facial identity scenarios. Our method significantly outperforms existing techniques, offering a more robust solution for privacy and copyright protection.

Chenyang Li, Wenbing Tang, Yihao Huang et al.

Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely encountered in everyday indoor environments. Errors under such contrived conditions have limited practical relevance, as real-world agents are unlikely to encounter such artificial patterns. In this work, we focus on indoor lighting, an intrinsic yet largely overlooked scene attribute that strongly influences navigation. We propose Indoor Lighting-based Adversarial Attack (ILA), a black-box framework that manipulates global illumination to disrupt VLN agents. Motivated by typical household lighting usage, we design two attack modes: Static Indoor Lighting-based Attack (SILA), where the lighting intensity remains constant throughout an episode, and Dynamic Indoor Lighting-based Attack (DILA), where lights are switched on or off at critical moments to induce abrupt illumination changes. We evaluate ILA on two state-of-the-art VLN models across three navigation tasks. Results show that ILA significantly increases failure rates while reducing trajectory efficiency, revealing previously unrecognized vulnerabilities of VLN agents to realistic indoor lighting variations.

Xiaojun Jia, Jindong Gu, Yihao Huang et al.

Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferability of adversarial examples on semantic segmentation has been largely overlooked. In this paper, we propose an effective two-stage adversarial attack strategy to improve the transferability of adversarial examples on semantic segmentation, dubbed TranSegPGD. Specifically, at the first stage, every pixel in an input image is divided into different branches based on its adversarial property. Different branches are assigned different weights for optimization to improve the adversarial performance of all pixels.We assign high weights to the loss of the hard-to-attack pixels to misclassify all pixels. At the second stage, the pixels are divided into different branches based on their transferable property which is dependent on Kullback-Leibler divergence. Different branches are assigned different weights for optimization to improve the transferability of the adversarial examples. We assign high weights to the loss of the high-transferability pixels to improve the transferability of adversarial examples. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets to demonstrate the effectiveness of the proposed method. The proposed adversarial attack method can achieve state-of-the-art performance.