Instead of building deep learning models from scratch, developers are more and more relying on adapting pre-trained models to their customized tasks. However, powerful pre-trained models may be misused for unethical or illegal tasks, e.g., privacy inference and unsafe content generation. In this paper, we introduce a pioneering learning paradigm, non-fine-tunable learning, which prevents the pre-trained model from being fine-tuned to indecent tasks while preserving its performance on the original task. To fulfill this goal, we propose SOPHON, a protection framework that reinforces a given pre-trained model to be resistant to being fine-tuned in pre-defined restricted domains. Nonetheless, this is challenging due to a diversity of complicated fine-tuning strategies that may be adopted by adversaries. Inspired by model-agnostic meta-learning, we overcome this difficulty by designing sophisticated fine-tuning simulation and fine-tuning evaluation algorithms. In addition, we carefully design the optimization process to entrap the pre-trained model within a hard-to-escape local optimum regarding restricted domains. We have conducted extensive experiments on two deep learning modes (classification and generation), seven restricted domains, and six model architectures to verify the effectiveness of SOPHON. Experiment results verify that fine-tuning SOPHON-protected models incurs an overhead comparable to or even greater than training from scratch. Furthermore, we confirm the robustness of SOPHON to three fine-tuning methods, five optimizers, various learning rates and batch sizes. SOPHON may help boost further investigations into safe and responsible AI.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
縮放
·
大語言模型
·
語言模型化
·
Learning
·
As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF's code is available at //github.com/OpenLLMAI/OpenRLHF.
Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.
Train-time data poisoning attacks threaten machine learning models by introducing adversarial examples during training, leading to misclassification. Current defense methods often reduce generalization performance, are attack-specific, and impose significant training overhead. To address this, we introduce a set of universal data purification methods using a stochastic transform, $\Psi(x)$, realized via iterative Langevin dynamics of Energy-Based Models (EBMs), Denoising Diffusion Probabilistic Models (DDPMs), or both. These approaches purify poisoned data with minimal impact on classifier generalization. Our specially trained EBMs and DDPMs provide state-of-the-art defense against various attacks (including Narcissus, Bullseye Polytope, Gradient Matching) on CIFAR-10, Tiny-ImageNet, and CINIC-10, without needing attack or classifier-specific information. We discuss performance trade-offs and show that our methods remain highly effective even with poisoned or distributionally shifted generative model training data.
Decentralized federated learning (DFL) captures FL settings where both (i) model updates and (ii) model aggregations are exclusively carried out by the clients without a central server. Existing DFL works have mostly focused on settings where clients conduct a fixed number of local updates between local model exchanges, overlooking heterogeneity and dynamics in communication and computation capabilities. In this work, we propose Decentralized Sporadic Federated Learning (DSpodFL), a DFL methodology built on a generalized notion of sporadicity in both local gradient and aggregation processes. DSpodFL subsumes many existing decentralized optimization methods under a unified algorithmic framework by modeling the per-iteration (i) occurrence of gradient descent at each client and (ii) exchange of models between client pairs as arbitrary indicator random variables, thus capturing heterogeneous and time-varying computation/communication scenarios. We analytically characterize the convergence behavior of DSpodFL for both convex and non-convex models, for both constant and diminishing learning rates, under mild assumptions on the communication graph connectivity, data heterogeneity across clients, and gradient noises, and show how our bounds recover existing results as special cases. Experiments demonstrate that DSpodFL consistently achieves improved training speeds compared with baselines under various system settings.
Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers' computational inefficiency on long sequences, but they have not performed as well as attention on important modalities such as language. We identify that a key weakness of such models is their inability to perform content-based reasoning, and make several improvements. First, simply letting the SSM parameters be functions of the input addresses their weakness with discrete modalities, allowing the model to selectively propagate or forget information along the sequence length dimension depending on the current token. Second, even though this change prevents the use of efficient convolutions, we design a hardware-aware parallel algorithm in recurrent mode. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba). Mamba enjoys fast inference (5$\times$ higher throughput than Transformers) and linear scaling in sequence length, and its performance improves on real data up to million-length sequences. As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics. On language modeling, our Mamba-3B model outperforms Transformers of the same size and matches Transformers twice its size, both in pretraining and downstream evaluation.
In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in varying contributions from individual clients to the final performance of the global model. In response, many contribution evaluation methods were proposed, where the server could evaluate the contribution made by each client and incentivize the high-contributing clients to sustain their long-term participation in FL. Existing studies mainly focus on developing new metrics or algorithms to better measure the contribution of each client. However, the security of contribution evaluation methods of FL operating in adversarial environments is largely unexplored. In this paper, we propose the first model poisoning attack on contribution evaluation methods in FL, termed ACE. Specifically, we show that any malicious client utilizing ACE could manipulate the parameters of its local model such that it is evaluated to have a high contribution by the server, even when its local training data is indeed of low quality. We perform both theoretical analysis and empirical evaluations of ACE. Theoretically, we show our design of ACE can effectively boost the malicious client's perceived contribution when the server employs the widely-used cosine distance metric to measure contribution. Empirically, our results show ACE effectively and efficiently deceive five state-of-the-art contribution evaluation methods. In addition, ACE preserves the accuracy of the final global models on testing inputs. We also explore six countermeasures to defend ACE. Our results show they are inadequate to thwart ACE, highlighting the urgent need for new defenses to safeguard the contribution evaluation methods in FL.
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from a generative model. Such an approach contradicts buffer-based approaches where sampling strategy plays an important role. We propose to bridge this gap by incorporating classifier guidance into the diffusion process to produce rehearsal examples specifically targeting information forgotten by a continuously trained model. This approach enables the generation of samples from preceding task distributions, which are more likely to be misclassified in the context of recently encountered classes. Our experimental results show that GUIDE significantly reduces catastrophic forgetting, outperforming conventional random sampling approaches and surpassing recent state-of-the-art methods in continual learning with generative replay.
In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through uploading poisoned local models, causing misclassification to a target class when encountering attacker-defined triggers. Existing backdoor defenses show inconsistent performance under different system and adversarial settings, especially when the malicious updates are made statistically close to the benign ones. In this paper, we first reveal the fact that planting subsequent backdoors with the same target label could significantly help to maintain the accuracy of previously planted backdoors, and then propose a novel proactive backdoor detection mechanism for FL named BackdoorIndicator, which has the server inject indicator tasks into the global model leveraging out-of-distribution (OOD) data, and then utilizing the fact that any backdoor samples are OOD samples with respect to benign samples, the server, who is completely agnostic of the potential backdoor types and target labels, can accurately detect the presence of backdoors in uploaded models, via evaluating the indicator tasks. We perform systematic and extensive empirical studies to demonstrate the consistently superior performance and practicality of BackdoorIndicator over baseline defenses, across a wide range of system and adversarial settings.
Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve the generalization capability. However, the data heterogeneity between sources may lead models to gradually forget previously acquired knowledge when undergoing cross-training to adapt to new tasks or data sources. We argue that integrating personalized and global knowledge to gather information from multiple perspectives could potentially improve performance. To achieve this goal, this paper presents a novel approach that enhances federated learning through a cross-training scheme incorporating multi-view information. Specifically, the proposed method, termed FedCT, includes three main modules, where the consistency-aware knowledge broadcasting module aims to optimize model assignment strategies, which enhances collaborative advantages between clients and achieves an efficient federated learning process. The multi-view knowledge-guided representation learning module leverages fused prototypical knowledge from both global and local views to enhance the preservation of local knowledge before and after model exchange, as well as to ensure consistency between local and global knowledge. The mixup-based feature augmentation module aggregates rich information to further increase the diversity of feature spaces, which enables the model to better discriminate complex samples. Extensive experiments were conducted on four datasets in terms of performance comparison, ablation study, in-depth analysis and case study. The results demonstrated that FedCT alleviates knowledge forgetting from both local and global views, which enables it outperform state-of-the-art methods.
Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts in real-world scenarios. To tackle the problem, numerous debias approaches have been proposed and benchmarked on datasets intentionally designed with severe biases. However, it remains to be asked: \textit{1. Do existing benchmarks really capture biases in the real world? 2. Can existing debias methods handle biases in the real world?} To answer the questions, we revisit biased distributions in existing benchmarks and real-world datasets, and propose a fine-grained framework for analyzing dataset bias by disentangling it into the magnitude and prevalence of bias. We observe and theoretically demonstrate that existing benchmarks poorly represent real-world biases. We further introduce two novel biased distributions to bridge this gap, forming a nuanced evaluation framework for real-world debiasing. Building upon these results, we evaluate existing debias methods with our evaluation framework. Results show that existing methods are incapable of handling real-world biases. Through in-depth analysis, we propose a simple yet effective approach that can be easily applied to existing debias methods, named Debias in Destruction (DiD). Empirical results demonstrate the superiority of DiD, improving the performance of existing methods on all types of biases within the proposed evaluation framework.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191