45 citations · 138 across the 20 of their papers we have counts for
21 papers
Typographic Attacks in a Multi-Image Setting
Xiaomeng Wang, Zhengyu Zhao, Martha Larson
Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we intr…
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
Junhao Zheng, Chenhao Lin, Jiahao Sun +3
Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against…
Adversarial Example Soups: Improving Transferability and Stealthiness for Free
Bo Yang, Hengwei Zhang, Jindong Wang +4
Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing…
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
Qiwei Tian, Chenhao Lin, Zhengyu Zhao +2
Adversarial training has achieved substantial performance in defending image retrieval against adversarial examples. However, existing studies in deep metric learning (DML) still s…
Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
Yugeng Liu, Tianshuo Cong, Zhengyu Zhao +3
Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on…
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Yihan Ma, Zhengyu Zhao, Xinlei He +3
Large text-to-image models have shown remarkable performance in synthesizing high-quality images. In particular, the subject-driven model makes it possible to personalize the image…
Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantization
Yulong Yang, Chenhao Lin, Qian Li +6
Quantized neural networks (QNNs) have received increasing attention in resource-constrained scenarios due to their exceptional generalizability. However, their robustness against r…
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
Zhuoran Liu, Zhengyu Zhao, Martha Larson
Perturbative availability poisons (PAPs) add small changes to images to prevent their use for model training. Current research adopts the belief that practical and effective approa…
Generative Poisoning Using Random Discriminators
Dirren van Vlijmen, Alex Kolmus, Zhuoran Liu +2
We introduce ShortcutGen, a new data poisoning attack that generates sample-dependent, error-minimizing perturbations by learning a generator. The key novelty of ShortcutGen is the…
Towards Good Practices in Evaluating Transfer Adversarial Attacks
Zhengyu Zhao, Hanwei Zhang, Renjue Li +3
Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two commo…
Membership Inference Attacks by Exploiting Loss Trajectory
Yiyong Liu, Zhengyu Zhao, Michael Backes +1
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's…
The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
Zhengyu Zhao, Nga Dang, Martha Larson
Adversarial images are created with the intention of causing an image classifier to produce a misclassification. In this paper, we propose that adversarial images should be evaluat…
Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detection
Hamid Bostani, Zhengyu Zhao, Zhuoran Liu +1
Machine Learning (ML) promises to enhance the efficacy of Android Malware Detection (AMD); however, ML models are vulnerable to realistic evasion attacks--crafting realizable Adver…
Going Grayscale: The Road to Understanding and Improving Unlearnable Examples
Zhuoran Liu, Zhengyu Zhao, Alex Kolmus +4
Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i.e. images whose content cannot be used to improve a classifier during…
On Success and Simplicity: A Second Look at Transferable Targeted Attacks
Zhengyu Zhao, Zhuoran Liu, Martha Larson
Achieving transferability of targeted attacks is reputed to be remarkably difficult. Currently, state-of-the-art approaches are resource-intensive because they necessitate training…
Screen Gleaning: A Screen Reading TEMPEST Attack on Mobile Devices Exploiting an Electromagnetic Side Channel
Zhuoran Liu, Niels Samwel, Léo Weissbart +4
We introduce screen gleaning, a TEMPEST attack in which the screen of a mobile device is read without a visual line of sight, revealing sensitive information displayed on the phone…
Adversarial Image Color Transformations in Explicit Color Filter Space
Zhengyu Zhao, Zhuoran Liu, Martha Larson
Deep Neural Networks have been shown to be vulnerable to adversarial images. Conventional attacks strive for indistinguishable adversarial images with strictly restricted perturbat…
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
Zhengyu Zhao, Zhuoran Liu, Martha Larson
We introduce an approach that enhances images using a color filter in order to create adversarial effects, which fool neural networks into misclassification. Our approach, Adversar…
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
Zhengyu Zhao, Zhuoran Liu, Martha Larson
The success of image perturbations that are designed to fool image classifier is assessed in terms of both adversarial effect and visual imperceptibility. The conventional assumpti…
Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval
Zhuoran Liu, Zhengyu Zhao, Martha Larson
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye. This paper presents an an…
From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition
Zhengyu Zhao, Martha Larson
As deep learning approaches to scene recognition emerge, they have continued to leverage discriminative regions at multiple scales, building on practices established by conventiona…