arXiv subjects

Yuan Xun

Publications and source records attributed to Yuan Xun.

10 recordsLinked to original sources

arXiv2025

TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations

While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced integration of core components (attack, defense, and evaluation methods) and an isolation between flexible evaluation frameworks and standardized benchmarking capabilities. These limitations hinder reliable cross-study comparisons and create unnecessary overhead for comprehensive risk assessment. To address these gaps, we present TeleAI-Safety, a modular and reproducible framework coupled with a systematic benchmark for rigorous LLM safety evaluation. Our framework integrates a broad collection of 19 attack methods (including one self-developed method), 29 defense methods, and 19 evaluation methods (including one self-developed method). With a curated attack corpus of 342 samples spanning 12 distinct risk categories, the TeleAI-Safety benchmark conducts extensive evaluations across 14 target models. The results reveal systematic vulnerabilities and model-specific failure cases, highlighting critical trade-offs between safety and utility, and identifying potential defense patterns for future optimization. In practical scenarios, TeleAI-Safety can be flexibly adjusted with customized attack, defense, and evaluation combinations to meet specific demands. We release our complete code and evaluation results to facilitate reproducible research and establish unified safety baselines.

cs.CR↗

arXiv2025

The Emotional Baby Is Truly Deadly: Does your Multimodal Large Reasoning Model Have Emotional Flattery towards Humans?

We observe that MLRMs oriented toward human-centric service are highly susceptible to user 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 framework 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 behavior.

cs.AI↗

arXiv2025

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations

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 and effective solution to escalating privacy concerns.

cs.CV↗

arXiv2025

Robust Anti-Backdoor Instruction Tuning in LVLMs

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually developed for single-modal visual or language models under fully parameter-adjustable settings or rely on supervisory knowledge during training. However, in real-world scenarios, defenders cannot modify frozen visual encoders or core LLM parameters, nor possess prior knowledge of unknown trigger patterns or target responses. Motivated by the empirical finding that LVLMs readily overfit to fixed, unknown triggers, which can embed malicious associations during adapter-level tuning, we aim to design a defense that operates without access to core weights or attack priors. To this end, we introduce a lightweight, certified-agnostic defense framework, Robust Instruction Tuning, that finetunes only adapter modules and text embedding layers under instruction tuning. Our method integrates two complementary regularizations: (1) Input Diversity Regularization, which perturbs trigger components across training samples to disrupt consistent spurious cues; and (2) Anomalous Activation Regularization, which dynamically sparses adapter weights exhibiting abnormally sharp activations linked to backdoor patterns. These mechanisms jointly guide the model toward learning semantically grounded representations rather than memorizing superficial trigger-response mappings. Extensive experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero, with an increase in training cost of less than 15%.

cs.CR↗

arXiv2025

PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors

Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns. Malicious actors can misuse these models to generate unauthorized portraits or artistic style replicas. Existing proactive defenses primarily rely on applying adversarial perturbations to reference images to disrupt training. However, these approaches face limitations: they assume all training images are pre-perturbed and are prone to failure when datasets contain unperturbed images or undergo minor data transformations. In this paper, we introduce PersGuard, a novel backdoor-based framework designed to prevent unauthorized personalization of pre-trained T2I diffusion models. Unlike perturbation-based methods, we assume protectors can embed protective backdoors into the models before their release. This mechanism ensures that if a downstream user fine-tunes the model on protected images, the model retains the backdoor and generates predefined protective outputs; conversely, for unprotected images, the backdoor is effectively removed during fine-tuning to ensure normal model utility. We formulate the backdoor injection as a unified optimization problem incorporating three objectives: a backdoor behavior loss to activate protection, a prior preservation loss to maintain standard generation capabilities, and a novel backdoor retention loss. The retention loss is specifically designed to mirror personalization loss, ensuring the backdoor remains robust during downstream fine-tuning. Extensive experiments across gray-box and black-box settings, multi-object protection, and facial identity protection demonstrate that PersGuard provides superior privacy protection compared to existing perturbation-based methods.

cs.CV↗

arXiv2024

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

Pre-trained large models for multimodal contrastive learning, such as CLIP, have been widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks. This poses significant risks to downstream model training. In response to such potential threats, finetuning offers a simpler and more efficient defense choice compared to retraining large models with augmented data. In the supervised learning domain, fine-tuning defense strategies can achieve excellent defense performance. However, in the unsupervised and semi-supervised domain, we find that when CLIP faces some complex attack techniques, the existing fine-tuning defense strategy, CleanCLIP, has some limitations on defense performance. The synonym substitution of its text-augmentation is insufficient to enhance the text feature space. To compensate for this weakness, we improve it by proposing a fine-grained \textbf{T}ext \textbf{A}lignment \textbf{C}leaner (TA-Cleaner) to cut off feature connections of backdoor triggers. We randomly select a few samples for positive and negative subtext generation at each epoch of CleanCLIP, and align the subtexts to the images to strengthen the text self-supervision. We evaluate the effectiveness of our TA-Cleaner against six attack algorithms and conduct comprehensive zero-shot classification tests on ImageNet1K. Our experimental results demonstrate that TA-Cleaner achieves state-of-the-art defensiveness among finetuning-based defense techniques. Even when faced with the novel attack technique BadCLIP, our TA-Cleaner outperforms CleanCLIP by reducing the ASR of Top-1 and Top-10 by 52.02\% and 63.88\%, respectively.

cs.CV↗

arXiv2024

Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may unauthorizedly exploit image-text data for model training, potentially including personal and privacy-sensitive information. Recent works propose generating unlearnable examples by adding imperceptible perturbations to training images to build shortcuts for protection. However, they are designed for unimodal classification, which remains largely unexplored in MCL. We first explore this context by evaluating the performance of existing methods on image-caption pairs, and they do not generalize effectively to multimodal data and exhibit limited impact to build shortcuts due to the lack of labels and the dispersion of pairs in MCL. In this paper, we propose Multi-step Error Minimization (MEM), a novel optimization process for generating multimodal unlearnable examples. It extends the Error-Minimization (EM) framework to optimize both image noise and an additional text trigger, thereby enlarging the optimized space and effectively misleading the model to learn the shortcut between the noise features and the text trigger. Specifically, we adopt projected gradient descent to solve the noise minimization problem and use HotFlip to approximate the gradient and replace words to find the optimal text trigger. Extensive experiments demonstrate the effectiveness of MEM, with post-protection retrieval results nearly half of random guessing, and its high transferability across different models. Our code is available on the https://github.com/thinwayliu/Multimodal-Unlearnable-Examples

cs.MM↗

arXiv2024

A Survey on Transferability of Adversarial Examples across Deep Neural Networks

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has also brought to light a concerning vulnerability: adversarial examples. These crafted inputs, imperceptible to humans, can manipulate machine learning models into making erroneous predictions, raising concerns for safety-critical applications. An intriguing property of this phenomenon is the transferability of adversarial examples, where perturbations crafted for one model can deceive another, often with a different architecture. This intriguing property enables black-box attacks which circumvents the need for detailed knowledge of the target model. This survey explores the landscape of the adversarial transferability of adversarial examples. We categorize existing methodologies to enhance adversarial transferability and discuss the fundamental principles guiding each approach. While the predominant body of research primarily concentrates on image classification, we also extend our discussion to encompass other vision tasks and beyond. Challenges and opportunities are discussed, highlighting the importance of fortifying DNNs against adversarial vulnerabilities in an evolving landscape.

cs.CV↗

arXiv2024

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the possibility of backdoor attacks. These attacks subtly embed malicious behaviors within the model during training, which can be activated by specific triggers in the inference phase, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the adverse impacts of such attacks, these defenses often degrade the clean accuracy and necessitate the construction of extensive clean training pairs. In this paper, we explore the possibility of a less-cost defense from the perspective of model unlearning, that is, whether the model can be made to quickly \textbf{u}nlearn \textbf{b}ackdoor \textbf{t}hreats (UBT) by constructing a small set of poisoned samples. Specifically, we strengthen the backdoor shortcuts to discover suspicious samples through overfitting training prioritized by weak similarity samples. Building on the initial identification of suspicious samples, we introduce an innovative token-based localized forgetting training regime. This technique specifically targets the poisoned aspects of the model, applying a focused effort to unlearn the backdoor associations and trying not to damage the integrity of the overall model. Experimental results show that our method not only ensures a minimal success rate for attacks, but also preserves the model's high clean accuracy.

cs.CV↗

arXiv2023

Does Few-shot Learning Suffer from Backdoor Attacks?

The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored. We first explore this topic by first evaluating the performance of the existing backdoor attack methods on few-shot learning scenarios. Unlike in standard supervised learning, existing backdoor attack methods failed to perform an effective attack in FSL due to two main issues. Firstly, the model tends to overfit to either benign features or trigger features, causing a tough trade-off between attack success rate and benign accuracy. Secondly, due to the small number of training samples, the dirty label or visible trigger in the support set can be easily detected by victims, which reduces the stealthiness of attacks. It seemed that FSL could survive from backdoor attacks. However, in this paper, we propose the Few-shot Learning Backdoor Attack (FLBA) to show that FSL can still be vulnerable to backdoor attacks. Specifically, we first generate a trigger to maximize the gap between poisoned and benign features. It enables the model to learn both benign and trigger features, which solves the problem of overfitting. To make it more stealthy, we hide the trigger by optimizing two types of imperceptible perturbation, namely attractive and repulsive perturbation, instead of attaching the trigger directly. Once we obtain the perturbations, we can poison all samples in the benign support set into a hidden poisoned support set and fine-tune the model on it. Our method demonstrates a high Attack Success Rate (ASR) in FSL tasks with different few-shot learning paradigms while preserving clean accuracy and maintaining stealthiness. This study reveals that few-shot learning still suffers from backdoor attacks, and its security should be given attention.

cs.CR↗