19 papers
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4
Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path,…
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
Tingchao Fu, Wenkai Wang, Fanxiao Li +6
Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from…
CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models
Renyang Liu, Jiale Li, Jie Zhang +6
Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative r…
REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
Yong Zou, Haoran Li, Fanxiao Li +5
Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generat…
PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
Haoran Li, Renyang Liu, Hongjia Liu +3
Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defen…
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
Renyang Liu, Kangjie Chen, Han Qiu +4
Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to…
Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
Renyang Liu, Guanlin Li, Tianwei Zhang +1
Recent advances in image generation models (IGMs), particularly diffusion-based architectures such as Stable Diffusion (SD), have markedly enhanced the quality and diversity of AI-…
Rethinking Machine Unlearning in Image Generation Models
Renyang Liu, Wenjie Feng, Tianwei Zhang +3
With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service p…
Proxy-Embedding as an Adversarial Teacher: An Embedding-Guided Bidirectional Attack for Referring Expression Segmentation Models
Xingbai Chen, Tingchao Fu, Renyang Liu +2
Referring Expression Segmentation (RES) enables precise object segmentation in images based on natural language descriptions, offering high flexibility and broad applicability in r…
D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized and Natural Images through Multimodal Guidance
Renyang Liu, Ziyu Lyu, Wei Zhou +1
In the rapidly evolving field of Artificial Intelligence Generated Content (AIGC), a central challenge is distinguishing AI-synthesized images from natural ones. Despite the impres…
STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Renyang Liu, Kwok-Yan Lam, Wei Zhou +4
Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existin…
SSTA: Salient Spatially Transformed Attack
Renyang Liu, Wei Zhou, Sixin Wu +2
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, es…
DTA: Distribution Transform-based Attack for Query-Limited Scenario
Renyang Liu, Wei Zhou, Xin Jin +3
In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is…
Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Bingbing Song, Derui Wang, Tianwei Zhang +3
As an emerging concept, steganography without embedding (SWE) hides a secret message without directly embedding it into a cover. Thus, SWE has the unique advantage of being immune…
Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?
Renyang Liu, Jun Zhao, Xing Chu +3
With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms. Recent progress shows…
Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networks
Renyang Liu, Wei Zhou, Jinhong Zhang +3
Recently, Graph Neural Networks (GNNs), including Homogeneous Graph Neural Networks (HomoGNNs) and Heterogeneous Graph Neural Networks (HeteGNNs), have made remarkable progress in…
AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings
Renyang Liu, Jinhong Zhang, Haoran Li +3
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks. Despite the significant progress in the attack success rate that has bee…
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack
Renyang Liu, Jinhong Zhang, Kwok-Yan Lam +2
Previous studies have revealed that artificial intelligence (AI) systems are vulnerable to adversarial attacks. Among them, model extraction attacks fool the target model by genera…
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
Renyang Liu, Wei Zhou, Tianwei Zhang +3
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast…