Search Results for author:
Found 20 papers, 12 papers with code
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0. 643 vs. 0. 640 in terms of $F_1$-score).
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
In particular, to help the watermark survive the subject-driven synthesis, we incorporate the synthesis process in learning GenWatermark by fine-tuning the detector with synthesized images for a specific subject.
Generated Graph Detection
Graph generative models become increasingly effective for data distribution approximation and data augmentation.
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Our evaluation result shows that 24% of the generated images using DreamBooth are hateful meme variants that present the features of the original hateful meme and the target individual/community; these generated images are comparable to hateful meme variants collected from the real world.
MGTBench: Benchmarking Machine-Generated Text Detection
Nonetheless, we note that only a small fraction of adversarial-crafted perturbations on MGTs can evade the ChatGPT Detector, thus highlighting the need for more robust MGT detection methods.
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks.
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Backdoor attacks represent one of the major threats to machine learning models.
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
The dissemination of hateful memes online has adverse effects on social media platforms and the real world.
Backdoor Attacks in the Supply Chain of Masked Image Modeling
Different from previous work, we are the first to systematically threat modeling on SSL in every phase of the model supply chain, i. e., pre-training, release, and downstream phases.
Data Poisoning Attacks Against Multimodal Encoders
Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.
Auditing Membership Leakages of Multi-Exit Networks
Furthermore, we propose a hybrid attack that exploits the exit information to improve the performance of existing attacks.
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
Finally, we find that data augmentation degrades the performance of existing attacks to a larger extent, and we propose an adaptive attack using augmentation to train shadow and attack models that improve attack performance.
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.
SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders
Recent research has shown that the machine learning model's copyright is threatened by model stealing attacks, which aim to train a surrogate model to mimic the behavior of a given model.
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images.
Model Stealing Attacks Against Inductive Graph Neural Networks
Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.
Node-Level Membership Inference Attacks Against Graph Neural Networks
To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced.
Quantifying and Mitigating Privacy Risks of Contrastive Learning
Our experimental results show that contrastive models trained on image datasets are less vulnerable to membership inference attacks but more vulnerable to attribute inference attacks compared to supervised models.
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
As a result, we lack a comprehensive picture of the risks caused by the attacks, e. g., the different scenarios they can be applied to, the common factors that influence their performance, the relationship among them, or the effectiveness of possible defenses.
Stealing Links from Graph Neural Networks
In this work, we propose the first attacks to steal a graph from the outputs of a GNN model that is trained on the graph.
