355 citations · 465 across the 37 of their papers we have counts for
37 papers
Adversarial Backdoor Defense in CLIP
Junhao Kuang, Siyuan Liang, Jiawei Liang +2
Multimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks. While current backdoor defense methods primarily employ co…
Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
Tianyuan Zhang, Lu Wang, Jiaqi Kang +5
Recent advances in deep learning have markedly improved autonomous driving (AD) models, particularly end-to-end systems that integrate perception, prediction, and planning stages,…
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…
Compromising Embodied Agents with Contextual Backdoor Attacks
Aishan Liu, Yuguang Zhou, Xianglong Liu +9
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal…
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning
Xinwei Liu, Xiaojun Jia, Yuan Xun +2
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,…
LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
Tianyuan Zhang, Lu Wang, Hainan Li +5
Lane detection (LD) is an essential component of autonomous driving systems, providing fundamental functionalities like adaptive cruise control and automated lane centering. Existi…
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
Zonghao Ying, Aishan Liu, Tianyuan Zhang +4
In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks pr…
Towards Robust Physical-world Backdoor Attacks on Lane Detection
Xinwei Zhang, Aishan Liu, Tianyuan Zhang +2
Deep learning-based lane detection (LD) plays a critical role in autonomous driving systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks. Existin…
GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
Yisong Xiao, Aishan Liu, QianJia Cheng +6
Large Vision-Language Models (LVLMs) have been widely adopted in various applications; however, they exhibit significant gender biases. Existing benchmarks primarily evaluate gende…
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
Siyuan Liang, Jiawei Liang, Tianyu Pang +5
Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static sett…
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
Siyuan Liang, Wei Wang, Ruoyu Chen +5
With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detector…
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
Siyuan Liang, Kuanrong Liu, Jiajun Gong +4
Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the ope…
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…
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
Xiaoxia Li, Siyuan Liang, Jiyi Zhang +3
Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where craf…
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Jiawei Liang, Siyuan Liang, Man Luo +4
Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed t…
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…
Does Few-shot Learning Suffer from Backdoor Attacks?
Xinwei Liu, Xiaojun Jia, Jindong Gu +3
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.…
Pre-trained Trojan Attacks for Visual Recognition
Aishan Liu, Xinwei Zhang, Yisong Xiao +6
Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors with…
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…
Improving Adversarial Transferability by Stable Diffusion
Jiayang Liu, Siyu Zhu, Siyuan Liang +4
Deep neural networks (DNNs) are susceptible to adversarial examples, which introduce imperceptible perturbations to benign samples, deceiving DNN predictions. While some attack met…
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
Siyuan Liang, Mingli Zhu, Aishan Liu +3
Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learn…
Face Encryption via Frequency-Restricted Identity-Agnostic Attacks
Xin Dong, Rui Wang, Siyuan Liang +2
Billions of people are sharing their daily live images on social media everyday. However, malicious collectors use deep face recognition systems to easily steal their biometric inf…
Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks
Jun Guo, Aishan Liu, Xingyu Zheng +4
Despite the broad application of Machine Learning models as a Service (MLaaS), they are vulnerable to model stealing attacks. These attacks can replicate the model functionality by…
Diversifying the High-level Features for better Adversarial Transferability
Zhiyuan Wang, Zeliang Zhang, Siyuan Liang +1
Given the great threat of adversarial attacks against Deep Neural Networks (DNNs), numerous works have been proposed to boost transferability to attack real-world applications. How…