论文检索

Social Aspects · Trustworthy Machine Learning

Zhixin Xie, Xurui Song, Jun Luo

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs’ safety alignment via fine-tuning stand out due to its stable jailbreak performance. In particular, a recent study indicates that fine-tuning with as few as 10 harmful question-answer (QA) pairs can lead to successful jailbreaking across various harmful questions. However, such malicious fine-tuning attacks are readily detectable and hence thwarted by moderation models. In this paper, we demonstrate that LLMs can be jailbroken by fine-tuning with only 10 benign QA pairs; our attack exploits the increased sensitivity of LLMs to fine-tuning data after being overfitted. Specifically, our fine-tuning process starts with overfitting an LLM via fine-tuning with benign QA pairs involving identical refusal answers. Further fine-tuning is then performed with standard benign answers, causing the overfitted LLM to forget the refusal attitude and thus provide compliant answers regardless of the harmfulness of a question. We implement our attack on the ten LLMs and compare it with five existing baselines. Experiments demonstrate that our method achieves significant advantages in both attack effectiveness and attack stealth. Our findings expose previously unreported security vulnerabilities in current LLMs and provide a new perspective on understanding how LLMs’ security is compromised, even with benign fine-tuning. Our code is available at https://github.com/ZHIXINXIE/ten_benign.git.

General Machine Learning · Representation Learning

Raphael Romero, Tijl De Bie, Nick Heard, Alexander Modell

Detecting structural change in dynamic network data has wide-ranging applications. Existing approaches typically divide the data into time bins, extract network features within each bin, and then compare these features over time. This introduces an inherent tradeoff between temporal resolution and the statistical stability of the extracted features. Despite this tradeoff, reminiscent of time–frequency tradeoffs in signal processing, most methods rely on a \emph{fixed temporal resolution}. Choosing an appropriate resolution parameter is typically difficult, and can be especially problematic in domains like cybersecurity, where anomalous behavior may emerge at multiple time scales. We address this challenge by proposing ANIE ($\textbf{A}$daptive $\textbf{N}$etwork $\textbf{I}$ntensity $\textbf{E}$stimation), a multi-resolution framework designed to automatically identify the time scales at which network structure evolves, enabling the joint detection of both rapid and gradual changes. Modeling interactions as Poisson processes, our method proceeds in two steps: (1) estimating a low-dimensional subspace of node behavior, and (2) deriving a set of novel *empirical affinity coefficients* that measure change in interaction intensity between latent factors and support statistical testing for structural change across time scales. We provide theoretical guarantees for subspace estimation and the asymptotic behavior of the affinity coefficients, enabling model-based change detection. Experiments on synthetic networks show that ANIE adapts to the appropriate time resolution, and is able to capture sharp structural changes while remaining robust to noise. Furthermore, applications to real-world data showcase the practical benefits of ANIE’s multiresolution approach to detecting structural change over fixed resolution methods. An open-source implementation of the method is available at [https://github.com/aida-ugent/anie].

Applications · Robotics

Xueyang Zhou, Guiyao Tie, Guowen Zhang, Hecheng Wang, Pan Zhou, Lichao Sun

Vision-Language-Action (VLA) models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities. Unlike traditional adversarial perturbations, backdoor attacks represent a stealthier, persistent, and practically significant threat—particularly under the emerging Training-as-a-Service paradigm—but remain largely unexplored in the context of VLA models. To address this gap, we propose **BadVLA**, a backdoor attack method based on Objective-Decoupled Optimization, which for the first time exposes the backdoor vulnerabilities of VLA models. Specifically, it consists of a two-stage process: (1) explicit feature-space separation to isolate trigger representations from benign inputs, and (2) conditional control deviations that activate only in the presence of the trigger, while preserving clean-task performance. Empirical results on multiple VLA benchmarks demonstrate that BadVLA consistently achieves near-100\% attack success rates with minimal impact on clean task accuracy. Further analyses confirm its robustness against common input perturbations, task transfers, and model fine-tuning, underscoring critical security vulnerabilities in current VLA deployments. Our work offers the first systematic investigation of backdoor vulnerabilities in VLA models, highlighting an urgent need for secure and trustworthy embodied model design practices.

General Machine Learning · Causality

Sarah Mameche, Janis Kalofolias, Jilles Vreeken

Real-world datasets are often a combination of unobserved subpopulations that follow distinct causal generating processes. In an observational study, for example, participants may fall into unknown groups that either (a) respond effectively to a drug, or (b) show no response due to drug resistance. Not accounting for such heterogeneity then risks biased estimates of drug effectiveness. In this work, we formulate this setting through a causal mixture model, in which the data-generating process of each variable depends on latent group membership (a or b). Specifically, we model each variable as a mixture of structural causal equation models, where latent categorical (mixing) variables index assignment to subpopulations. Unlike prior work, the approach allows for multiple independent mixing variables, each affecting distinct sets of observed variables. To infer both the graph, mixing variables, and assignments jointly, we integrate mixture modeling into score-based causal discovery; show theoretically that the resulting scoring criterion is consistent; and demonstrate empirically that the resulting causal discovery approach discovers the causal model in synthetic and real-world evaluations.

Theory · Learning Theory

Yifan Zhu, Lijia Yu, Xiao-Shan Gao

In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying dataset ownership or safeguarding private data from unauthorized use. However, these developments have the potential to cause misunderstandings and conflicts, as data poisoning has traditionally been regarded as a security threat to machine learning systems. To address this issue, it is imperative for harmless poisoning generators to claim ownership of their generated datasets, enabling users to identify potential poisoning to prevent misuse. In this paper, we propose the deployment of watermarking schemes as a solution to this challenge. We introduce two provable and practical watermarking approaches for data poisoning: post-poisoning watermarking and poisoning-concurrent watermarking. Our analyses demonstrate that when the watermarking length is $\Theta(\sqrt{d}/\epsilon_w)$ for post-poisoning watermarking, and falls within the range of $\Theta(1/\epsilon_w^2)$ to $O(\sqrt{d}/\epsilon_p)$ for poisoning-concurrent watermarking, the watermarked poisoning dataset provably ensures both watermarking detectability and poisoning utility, certifying the practicality of watermarking under data poisoning attacks. We validate our theoretical findings through experiments on several attacks, models, and datasets.

Social Aspects · Trustworthy Machine Learning

Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate strong reasoning capabilities after post-training different general large language models on diverse chain-of-thought (CoT) datasets. However, this additional training frequently comes at the cost of reduced safety, as the fine-tuned or post-trained models tend to exhibit more harmful behaviors compared with the regular LLMs before post-training or fine-tuning, potentially leading to harmful outcomes due to their enhanced capabilities. Taking LRMs as an example, we first investigate the underlying cause of this safety degradation in this paper. Our analysis reveals that post-training can mask the original safety mechanisms of the base LLM, while over-amplifying representations related to their post-training ability. But luckily, we also find that LRMs' safety mechanisms still exist instead of being removed during their post-training. Based on these findings, we propose a lightweight and cost-effective solution called SafeReAct that restores the suppressed safety behaviors by aligning with LoRA adapters on a few layers. Experiments on four state-of-the-art LRMs show that our method significantly improves safety on harmful prompts without compromising reasoning performance. Besides LRMs, additional results on other domain-specific LLMs, like medical models, further confirm the generality and effectiveness of our approach.

Theory · Everything Else

Yiheng Lin, Christopher Yeh, Zaiwei Chen, Adam Wierman

We study the value of stochastic predictions in online optimal control with random disturbances. Prior work provides performance guarantees based on prediction error but ignores the stochastic dependence between predictions and disturbances. We introduce a general framework modeling their joint distribution and define "prediction power" as the control cost improvement from the optimal use of predictions compared to ignoring the predictions. In the time-varying Linear Quadratic Regulator (LQR) setting, we derive a closed-form expression for prediction power and discuss its mismatch with prediction accuracy and connection with online policy optimization. To extend beyond LQR, we study general dynamics and costs. We establish a lower bound on prediction power under two sufficient conditions that generalize the properties of the LQR setting, characterizing the fundamental benefit of incorporating stochastic predictions. We apply this lower bound to non-quadratic costs and show that even weakly dependent predictions yield significant performance gains.

Social Aspects · Fairness, Equity, Justice and Safety

Hao Li, Xiaogeng Liu, CHIU Chun, Dianqi Li, Ning Zhang, Chaowei Xiao

Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities. By interacting with external environments through predefined tools, these agents can carry out complex user tasks. Nonetheless, this interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent’s behavior, potentially resulting in economic loss, privacy leakage, or system compromise. System-level defenses have recently shown promise by enforcing static or predefined policies, but they still face two key challenges: the ability to dynamically update security rules and the need for memory stream isolation. To address these challenges, we propose DRIFT, a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control- and data-level constraints. A Secure Planner first constructs a minimal function trajectory and a JSON-schema-style parameter checklist for each function node based on the user query. A Dynamic Validator then monitors deviations from the original plan, assessing whether changes comply with privilege limitations and the user's intent. Finally, an \textit{Injection Isolator} detects and masks any instructions that may conflict with the user query from the memory stream to mitigate long-term risks. We empirically validate the effectiveness of DRIFT on the AgentDojo and ASB benchmark, demonstrating its strong security performance while maintaining high utility across diverse models—showcasing both its robustness and adaptability. The code is released at https://github.com/SaFoLab-WISC/DRIFT.

Deep Learning · Robustness

Chantal Shaib, Vinith Suriyakumar, Byron Wallace, Marzyeh Ghassemi

For an LLM to correctly respond to an instruction it must understand both the semantics and the domain (i.e., subject area) of a given task-instruction pair. However, syntax can also convey implicit information. Recent work shows that \textit{syntactic templates}---frequent sequences of Part-of-Speech (PoS) tags---are prevalent in training data and often appear in model outputs. In this work we characterize syntactic templates, domain, and semantics in task-instruction pairs. We identify cases of spurious correlations between syntax and domain, where models learn to associate a domain with syntax during training; this can sometimes override prompt semantics. Using a synthetic training dataset, we find that the syntactic-domain correlation can lower performance (mean 0.51 +/- 0.06) on entity knowledge tasks in OLMo-2 models (1B-13B). We introduce an evaluation framework to detect this phenomenon in trained models, and show that it occurs on a subset of the FlanV2 dataset in open (OLMo-2-7B; Llama-4-Maverick), and closed (GPT-4o) models. Finally, we present a case study on the implications for LLM security, showing that unintended syntactic-domain correlations can be used to bypass refusals in OLMo-2-7B Instruct and GPT-4o. Our findings highlight two needs: (1) to explicitly test for syntactic-domain correlations, and (2) to ensure \textit{syntactic} diversity in training data, specifically within domains, to prevent such spurious correlations.

Xander Davies, Eric Winsor, Alexandra Souly, Tomek Korbak, Robert Kirk, Christian Schroeder de Witt, Yarin Gal

LLM developers deploy technical mitigations to prevent _fine-tuning misuse attacks_, attacks in which adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks against specific fine-tuning API defences; however, prior attacks training and/or inference samples can be easily flagged as suspicious. In this work, we show that defences of fine-tuning APIs that seek to detect individual harmful training or inference samples ('pointwise' detection) are _fundamentally limited_ in their ability to prevent fine-tuning attacks. We demonstrate a class of 'pointwise-undetectable' attacks that repurpose semantic or syntactic variations in benign model outputs to covertly transmit dangerous knowledge. Our attacks are composed solely of unsuspicious benign samples that can be collected from the model before fine-tuning, meaning training and inference samples are all individually benign and low-perplexity. We test our attacks against the OpenAI fine-tuning API, finding they succeed in eliciting answers to harmful multiple-choice questions, and that they evade an enhanced monitoring system we design that successfully detects other fine-tuning attacks. Our results showing fundamental limitations of defending against pointwise attacks suggest focusing research efforts on mitigations towards multi-point defences.

General Machine Learning · Representation Learning

Rishi Jha, Collin Zhang, Vitaly Shmatikov, John Morris

We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches. Our unsupervised approach translates any embedding to and from a universal latent representation (i.e., a universal semantic structure conjectured by the Platonic Representation Hypothesis). Our translations achieve high cosine similarity across model pairs with different architectures, parameter counts, and training datasets. The ability to translate unknown embeddings into a different space while preserving their geometry has serious implications for the security of vector databases. An adversary with access only to embedding vectors can extract sensitive information about the underlying documents, sufficient for classification and attribute inference.

Optimization · Neural Network Optimization

Advait Gadhikar, Tom Jacobs, chao zhou, Rebekka Burkholz

The performance gap between training sparse neural networks from scratch (PaI) and dense-to-sparse training presents a major roadblock for efficient deep learning. According to the Lottery Ticket Hypothesis, PaI hinges on finding a problem specific parameter initialization. As we show, to this end, determining correct parameter signs is sufficient. Yet, they remain elusive to PaI. To address this issue, we propose Sign-In, which employs a dynamic reparameterization that provably induces sign flips. Such sign flips are complementary to the ones that dense-to-sparse training can accomplish, rendering Sign-In as an orthogonal method. While our experiments and theory suggest performance improvements of PaI, they also carve out the main open challenge to close the gap between PaI and dense-to-sparse training.

Social Aspects · Trustworthy Machine Learning

Mohan Zhang, Yihua Zhang, Jinghan Jia, Zhangyang "Atlas" Wang, Sijia Liu, Tianlong Chen

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow by training a malicious adversarial embedding to induce perpetual reasoning loops. Specifically, the optimized embedding encourages transitional tokens (e.g., “Wait”, “But”) after reasoning steps, preventing the model from concluding its answer. A key challenge we identify is the continuous-to-discrete projection gap: naïve projections of adversarial embeddings to token sequences nullify the attack. To overcome this, we introduce a backdoor implantation strategy, enabling reliable activation through specific trigger tokens. Our method achieves a 100\% attack success rate across four advanced LRMs (Phi-RM, Nemotron-Nano, R1-Qwen, R1-Llama) and three math reasoning benchmarks, forcing models to generate up to their maximum token limits. The attack is also stealthy (in terms of causing negligible utility loss on benign user inputs) and remains robust against existing strategies trying to mitigate the overthinking issue. Our findings expose a critical and underexplored security vulnerability in LRMs from the perspective of reasoning (in)efficiency.

Deep Learning · Robustness

Yun Xing, Yue Cao, Nhat Chung, Jie Zhang, Ivor Tsang, Ming-Ming Cheng, Yang Liu, Lei Ma, Qing Guo

Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help revealing vulnerabilities before deployment. Previous works have shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated textures perform poorly in physical implementations, $\textit{i.e.}$, when deployed as patches, limiting their practical utility for stress-testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals among the repeated textures, creating a grid structure, significantly enhances the patch attack performance. Through extensive experimentation, we analyze how variations of this novel structure influence the adversarial effectiveness. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the interval structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack advanced stereo depth estimation methods of different paradigms, $\textit{i.e.}$, RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems. The code is officially released at: https://github.com/WiWiN42/DepthVanish

Deep Learning · Robustness

HAOTIAN XU, Qingsong Peng, Jie Shi, Huadi Zheng, YU LI, Cheng Zhuo

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well-studied, Bit-Flip Attacks (BFAs)—which exploit hardware vulnerabilities to corrupt model parameters and cause severe performance degradation—have received far less attention. Existing BFA methods suffer from key limitations: they fail to balance performance degradation and output naturalness, making them prone to discovery. In this paper, we introduce SilentStriker, the first stealthy bit-flip attack against LLMs that effectively degrades task performance while maintaining output naturalness. Our core contribution lies in addressing the challenge of designing effective loss functions for LLMs with variable output length and the vast output space. Unlike prior approaches that rely on output perplexity for attack loss formulation, which in-evidently degrade the output naturalness, we reformulate the attack objective by leveraging key output tokens as targets for suppression, enabling effective joint optimization of attack effectiveness and stealthiness. Additionally, we employ an iterative, progressive search strategy to maximize attack efficacy. Experiments show that SilentStriker significantly outperforms existing baselines, achieving successful attacks without compromising the naturalness of generated text.

Social Aspects · Trustworthy Machine Learning

Gaojian Xiong, Yu Sun, Jianhua Liu, Jian Cui, Jianwei Liu

While Large Language Models (LLMs) have gained remarkable success, they are consistently at risk of being stolen when deployed on untrusted edge devices. As a solution, TEE-based secure inference has been proposed to protect valuable model property. However, we identify a statistical vulnerability in existing protection methods, and furtherly compromise their security guarantees by proposed Model Stealing Attack with Prior. To eliminate this vulnerability, LoRO is presented in this paper, which leverages dense mask to completely obfuscate parameters. LoRO includes two innovations: (1) Low Rank Mask, which uses low-rank factors to generate dense masks efficiently. The computing complexity in TEE is hence reduced by an exponential amount to achieve inference speed up, while providing robust model confidentiality. (2) Factors Multiplexing, which reuses several cornerstone factors to generate masks for all layers. Compared to one-mask-per-layer, the secure memory requirement is reduced from GB-level to tens of MB, hence avoiding the hundred-fold latency introduced by secure memory paging. Experimental results indicate that LoRO achieve a $0.94\times$ Model Stealing (MS) accuracy, while SOTA methods presents $3.37\times$ at least. The averaged inference latency of LoRO is only $1.49\times$, compared to the $112\times$ of TEE-shielded inference. Moreover, LoRO results no accuracy loss, and requires no re-training and structure modification. LoRO can solve the concerns regarding model thefts on edge devices in an efficient and secure manner, facilitating the wide edge application of LLMs.

Social Aspects · Privacy-preserving Statistics and Machine Learning

Pukang Ye, Luo Junwei, Jiachen Shen, Saipan Zhou, Shangmin Dou, Zhenfu Cao, Hanzhe Yao, Xiaolei Dong, Yunbo Yang

Data duplication within large-scale corpora often impedes large language models' (LLMs) performance and privacy. In privacy-concerned federated learning scenarios, conventional deduplication methods typically rely on trusted third parties to perform uniform deletion, risking loss of informative samples while introducing privacy vulnerabilities. To address these gaps, we propose Federated ReWeighting (FedRW), the first privacy-preserving framework, to the best of our knowledge, that performs soft deduplication via sample reweighting instead of deletion in federated LLM training, without assuming a trusted third party. At its core, FedRW proposes a secure, frequency-aware reweighting protocol through secure multi-party computation, coupled with a parallel orchestration strategy to ensure efficiency and scalability. During training, FedRW utilizes an adaptive reweighting mechanism with global sample frequencies to adjust individual loss contributions, effectively improving generalization and robustness. Empirical results demonstrate that FedRW outperforms the state-of-the-art method by achieving up to $28.78\times$ speedup in preprocessing and approximately $11.42$\% improvement in perplexity, while offering enhanced security guarantees. FedRW thus establishes a new paradigm for managing duplication in federated LLM training.

Social Aspects · Privacy-preserving Statistics and Machine Learning

Jie Yan, Jing Liu, Zhong-Yuan Zhang

Federated clustering (FC) aims to discover global cluster structures across decentralized clients without sharing raw data, making privacy preservation a fundamental requirement. There are two critical challenges: (1) privacy leakage during collaboration, and (2) robustness degradation due to aggregation of proxy information from non-independent and identically distributed (Non-IID) local data, leading to inaccurate or inconsistent global clustering. Existing solutions typically rely on model-specific local proxies, which are sensitive to data heterogeneity and inherit inductive biases from their centralized counterparts, thus limiting robustness and generality. We propose Omni Federated Clustering (OmniFC), a unified and model-agnostic framework. Leveraging Lagrange coded computing, our method enables clients to share only encoded data, allowing exact reconstruction of the global distance matrix—a fundamental representation of sample relationships—without leaking private information, even under client collusion. This construction is naturally resilient to Non-IID data distributions. This approach decouples FC from model-specific proxies, providing a unified extension mechanism applicable to diverse centralized clustering methods. Theoretical analysis confirms both reconstruction fidelity and privacy guarantees, while comprehensive experiments demonstrate OmniFC's superior robustness, effectiveness, and generality across various benchmarks compared to state-of-the-art methods. Code will be released.

Social Aspects · Fairness, Equity, Justice and Safety

Yihan Wu, Georgios Milis, Ruibo Chen, Heng Huang

The rapid advancement of next-token-prediction models has led to widespread adoption across modalities, enabling the creation of realistic synthetic media. In the audio domain, while autoregressive speech models have propelled conversational interactions forward, the potential for misuse, such as impersonation in phishing schemes or crafting misleading speech recordings, has also increased. Security measures such as watermarking have thus become essential to ensuring the authenticity of digital media. Traditional statistical watermarking methods used for autoregressive language models face challenges when applied to autoregressive audio models, due to the inevitable ``retokenization mismatch'' - the discrepancy between original and retokenized discrete audio token sequences. To address this, we introduce Aligned-IS, a novel, distortion-free watermark, specifically crafted for audio generation models. This technique utilizes a clustering approach that treats tokens within the same cluster equivalently, effectively countering the retokenization mismatch issue. Our comprehensive testing on prevalent audio generation platforms demonstrates that Aligned-IS not only preserves the quality of generated audio but also significantly improves the watermark detectability compared to the state-of-the-art distortion-free watermarking adaptations, establishing a new benchmark in secure audio technology applications.

Deep Learning · Everything Else

Jiayang Liu, Siyuan Liang, Shiqian Zhao, Rong-Cheng Tu, Wenbo Zhou, Aishan Liu, Dacheng Tao, Siew Kei Lam

In recent years, fueled by the rapid advancement of diffusion models, text-to-video (T2V) generation models have achieved remarkable progress, with notable examples including Pika, Luma, Kling, and Open-Sora. Although these models exhibit impressive generative capabilities, they also expose significant security risks due to their vulnerability to jailbreak attacks, where the models are manipulated to produce unsafe content such as pornography, violence, or discrimination. Existing works such as T2VSafetyBench provide preliminary benchmarks for safety evaluation, but lack systematic methods for thoroughly exploring model vulnerabilities. To address this gap, we are the first to formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called \emph{T2V-OptJail}. This framework consists of two key optimization goals: bypassing the built-in safety filtering mechanisms to increase the attack success rate, preserving semantic consistency between the adversarial prompt and the unsafe input prompt, as well as between the generated video and the unsafe input prompt, to enhance content controllability. In addition, we introduce an iterative optimization strategy guided by prompt variants, where multiple semantically equivalent candidates are generated in each round, and their scores are aggregated to robustly guide the search toward optimal adversarial prompts. We conduct large-scale experiments on several T2V models, covering both open-source models (\textit{e.g.}, Open-Sora) and real commercial closed-source models (\textit{e.g.}, Pika, Luma, Kling). The experimental results show that the proposed method improves 11.4\% and 10.0\% over the existing state-of-the-art method (SoTA) in terms of attack success rate assessed by GPT-4, attack success rate assessed by human accessors, respectively, verifying the significant advantages of the method in terms of attack effectiveness and content control. This study reveals the potential abuse risk of the semantic alignment mechanism in the current T2V model and provides a basis for the design of subsequent jailbreak defense methods.