19 accepted papers
The rapid proliferation of pretrained models and open repositories has made model merging a convenient yet risky practice, allowing free-riders to combine fine-tuned models into a new multi-capability model without authorization. Such unauthorized model merging not only violates intellectual propert
Safety alignment of large language models is fragile: even small fine-tuning perturbations elastically revert behaviors toward those of the pre-training, with degradation inversely proportional to the size of the alignment set. We ask how to achieve safety alignment with \emph{minimal augmentation}.…
Generative AI models, particularly diffusion models (DMs), have demonstrated exceptional capabilities in high-quality image synthesis. However, their large memorization capacity raises significant privacy concerns, especially when trained on sensitive datasets. This paper introduces DP-LoRA, a surpr…
Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic (TA), which combines task vectors derived from fine-tuning,
Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass internal safeguards, underscoring the need to understand the failure modes of current safety strategies. R…
Differentially private (DP) synthetic data has become the de facto standard for releasing sensitive data. However, many DP generative models suffer from the low utility of synthetic data, especially for high-resolution images. On the other hand, one of the emerging techniques in parameter efficient…
Deep neural networks (DNNs) are known to be vulnerable to backdoor attacks. Specifically, the attacker endeavors to implant backdoors in the DNN model by injecting a set of poisoning samples such that the malicious model predicts target labels once the backdoor is triggered. The clean-image attack h…
Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical aspects of backdoor attacks and dataset distillation based…
Diffusion models for text-to-image (T2I) synthesis, such as Stable Diffusion (SD), have recently demonstrated exceptional capabilities for generating high-quality content. However, this progress has raised several concerns of potential misuse, particularly in creating copyrighted, prohibited, and re…
While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs. However, fine-tuning all parameters of LLMs requires significan…
Recently, quantum classifiers have been known to be vulnerable to adversarial attacks, where quantum classifiers are fooled by imperceptible noises to have misclassification. In this paper, we propose one first theoretical study that utilizing the added quantum random rotation noise can improve the…
Visual Prompting (VP) is an emerging and powerful technique that allows sample-efficient adaptation to downstream tasks by engineering a well-trained frozen source model. In this work, we explore the benefits of VP in constructing compelling neural network classifiers with differential privacy (DP).…
Adversarial examples causing evasive predictions are widely used to evaluate and improve the robustness of machine learning models. However, current studies focus on supervised learning tasks, relying on the ground truth data label, a targeted objective, or supervision from a trained classifier. In…
Despite an increased demand for valuable data, the privacy concerns associated with sensitive datasets present a barrier to data sharing. One may use differentially private generative models to generate synthetic data. Unfortunately, generators are typically restricted to generating images of low-re…
Deep neural networks have developed rapidly and have achieved out-standing performance in several tasks, such as image classification and natural language processing. However, recent studies have indicated that both digital and physical adversarial examples can fool neural networks. Face-recognition…
Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leaka…
Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, an…
Adversarial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. While being critical, we argue that solving this singular issue alone fails to provide a comprehensive robustness assessment. Even worse, the conclusions drawn from…
With the growing use of camera devices, the industry has many image datasets that provide more opportunities for collaboration between the machine learning community and industry. However, the sensitive information in the datasets discourages data owners from releasing these datasets. Despite recent…