Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code generation, biomedical analysis, and mathematical problem solving. However, this fine-tuning process often introduces a critical vulnerability: the systematic degradation of safety alignment, undermining ethical guidelines and increasing the risk of harmful outputs. Addressing this challenge, we introduce EnchTable, a novel framework designed to transfer and maintain safety alignment in downstream LLMs without requiring extensive retraining. EnchTable leverages a Neural Tangent Kernel (NTK)-based safety vector distillation method to decouple safety constraints from task-specific reasoning, ensuring compatibility across diverse model architectures and sizes. Additionally, our interference-aware merging technique effectively balances safety and utility, minimizing performance compromises across various task domains. We implemented a fully functional prototype of EnchTable on three different task domains and three distinct LLM architectures, and evaluated its performance through extensive experiments on eleven diverse datasets, assessing both utility and model safety. Our evaluations include LLMs from different vendors, demonstrating EnchTable's generalization capability. Furthermore, EnchTable exhibits robust resistance to static and dynamic jailbreaking attacks, outperforming vendor-released safety models in mitigating adversarial prompts. Comparative analyses with six parameter modification methods and two inference-time alignment baselines reveal that EnchTable achieves a significantly lower unsafe rate, higher utility score, and universal applicability across different task domains. Additionally, we validate EnchTable can be seamlessly integrated into various deployment pipelines without significant overhead.

Differentially private (DP) image synthesis aims to generate artificial images that retain the properties of a sensitive image dataset while protecting the privacy of individual images within the dataset. Despite recent advancements, we find that inconsistent--and sometimes flawed--evaluation protocols have been applied across studies. This not only impedes the understanding of current methods but also hinders future advancements in the field. To address the issue, this paper introduces DPImageBench, with thoughtful design across several dimensions: (1) Methods. We study twelve prominent methods and systematically characterize each based on model architecture, pretraining strategy, and privacy mechanism. (2) Evaluation. We include nine datasets and seven metrics to thoroughly assess these methods. Notably, we find that the common practice of selecting downstream classifiers based on the highest accuracy on sensitive test sets not only violates DP but also overestimates the utility. DPImageBench corrects for it. (3) Platform. Despite the wide variety of methods and evaluation protocols, DPImageBench provides a standardized interface that accommodates current and future implementations within a unified framework. With DPImageBench, we have several noteworthy findings. For example, contrary to the common wisdom that pretraining on public image datasets is usually beneficial, we find that the distributional similarity between pretraining and sensitive images significantly impacts the performance of the synthetic images and does not always yield improvements. The source code is available.

As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the *single-domain* of initial Gaussian noise for generation, which suffers from unsatisfactory robustness. This paper presents the first *dual-domain* DM watermarking approach using a pipelined injector to consistently embed watermarks in both the spatial and frequency domains. To further boost robustness against certain image manipulations and advanced attacks, we introduce a model-independent learnable Gaussian Noise Restorer (GNR) to refine Gaussian noise extracted from manipulated images and enhance detection robustness by integrating the detection scores of both watermarks. GaussMarker efficiently achieves state-of-the-art performance under eight image distortions and four advanced attacks across three versions of Stable Diffusion with better recall and lower false positive rates, as preferred in real applications.

Differentially private (DP) image synthesis aims to generate synthetic images from a sensitive dataset, alleviating the privacy leakage concerns of organizations sharing and utilizing synthetic images. Although previous methods have significantly progressed, especially in training diffusion models on sensitive images with DP Stochastic Gradient Descent (DP-SGD), they still suffer from unsatisfactory performance. In this work, inspired by curriculum learning, we propose a two-stage DP image synthesis framework, where diffusion models learn to generate DP synthetic images from easy to hard. Unlike existing methods that directly use DP-SGD to train diffusion models, we propose an easy stage in the beginning, where diffusion models learn simple features of the sensitive images. To facilitate this easy stage, we propose to use ‘central images’, simply aggregations of random samples of the sensitive dataset. Intuitively, although those central images do not show details, they demonstrate useful characteristics of all images and only incur minimal privacy costs, thus helping early-phase model training. We conduct experiments to present that on the average of four investigated image datasets, the fidelity and utility metrics of our synthetic images are 33.1% and 2.1% better than the state-of-the-art method. The replication package and datasets can be accessed online11.https://github.comJSunnierLee/DP-FETA.

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with environments. In offline RL, data providers share large pre-collected datasets, and others can train high-quality agents without interacting with the environments. This paradigm has demonstrated effectiveness in critical tasks like robot control, autonomous driving, etc. However, less attention is paid to investigating the security threats to the offline RL system. This paper focuses on backdoor attacks, where some perturbations are added to the data (observations) such that given normal observations, the agent takes high-rewards actions, and low-reward actions on observations injected with triggers. In this paper, we propose Baffle (Backdoor Attack for Offline Reinforcement Learning), an approach that automatically implants backdoors to RL agents by poisoning the offline RL dataset, and evaluate how different offline RL algorithms react to this attack. Our experiments conducted on four tasks and nine offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms has been immune to such a backdoor attack. More specifically, Baffle modifies 10% of the datasets for four tasks (3 robotic controls and 1 autonomous driving). Agents trained on the poisoned datasets perform well in normal settings. However, when triggers are presented, the agents’ performance decreases drastically by 63.2%, 53.9%, 64.7%, and 47.4% in the four tasks on average. The backdoor still persists after fine-tuning poisoned agents on clean datasets. We further show that the inserted backdoor is also hard to be detected by a popular defensive method. This paper calls attention to developing more effective protection for the open-source offline RL dataset.