69 citations · 157 across the 34 of their papers we have counts for
24 papers · 1 filter
SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization
Ziyi Fang, Jingzhi Li, Xiaojun Jia +3
Safety alignment of text-to-image diffusion models aims to suppress harmful content without compromising useful generation capabilities. However, preferences over completed images…
SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
Haobo Wang, Weiqi Luo, Xiaojun Jia +1
Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outp…
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
Tianrui Lou, Xiaojun Jia, Siyuan Liang +4
Physical adversarial attack methods expose the vulnerabilities of deep neural networks and pose a significant threat to safety-critical scenarios such as autonomous driving. Camouf…
GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
Xinwei Liu, Xiaojun Jia, Yuan Xun +2
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. Alth…
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
Xinwei Liu, Xiaojun Jia, Yuan Xun +2
Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns. Malicious actors can misuse…
Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks
Chen Zhou, Peng Cheng, Junfeng Fang +6
Multispectral object detection, utilizing RGB and TIR (thermal infrared) modalities, is widely recognized as a challenging task. It requires not only the effective extraction of fe…
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
Yuan Xun, Siyuan Liang, Xiaojun Jia +2
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. Thi…
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Tianrui Lou, Xiaojun Jia, Jindong Gu +4
Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are eas…
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
Sensen Gao, Xiaojun Jia, Xuhong Ren +2
Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs…
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
Jiawei Liang, Siyuan Liang, Aishan Liu +3
The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim…
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation
Bangyan He, Xiaojun Jia, Siyuan Liang +3
Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can l…
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization
Dongchen Han, Xiaojun Jia, Yang Bai +3
Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs…
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
Xiaojun Jia, Jindong Gu, Yihao Huang +4
Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferabili…
Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks
Xiaojun Jia, Jianshu Li, Jindong Gu +2
Adversarial training has shown promise in building robust models against adversarial examples. A major drawback of adversarial training is the computational overhead introduced by…
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
Jindong Gu, Xiaojun Jia, Pau de Jorge +9
The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing,…
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao +5
Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often…
Context-Aware Robust Fine-Tuning
Xiaofeng Mao, Yuefeng Chen, Xiaojun Jia +3
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sent…
A Large-scale Multiple-objective Method for Black-box Attack against Object Detection
Siyuan Liang, Longkang Li, Yanbo Fan +4
Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model info…
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Xiaojun Jia, Yong Zhang, Xingxing Wei +4
Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robus…
Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal
Xinwei Liu, Jian Liu, Yang Bai +4
As a common security tool, visible watermarking has been widely applied to protect copyrights of digital images. However, recent works have shown that visible watermarks can be rem…
LAS-AT: Adversarial Training with Learnable Attack Strategy
Xiaojun Jia, Yong Zhang, Baoyuan Wu +3
Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples…
Boosting Fast Adversarial Training with Learnable Adversarial Initialization
Xiaojun Jia, Yong Zhang, Baoyuan Wu +2
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face…
An Effective and Robust Detector for Logo Detection
Xiaojun Jia, Huanqian Yan, Yonglin Wu +3
In recent years, intellectual property (IP), which represents literary, inventions, artistic works, etc, gradually attract more and more people's attention. Particularly, with the…
ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples
Xiaojun Jia, Xingxing Wei, Xiaochun Cao +1
Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trai…