Diffusion models are increasingly deployed in real-world text-to-image services. These models, however, encode implicit assumptions about the world based on webscraped image-caption pairs used during training. Over time, such assumptions may become outdated, incorrect, or socially biased-leading to failures where the generated images misalign with users' expectations or evolving societal norms. Identifying and fixing such failures is challenging and, thus, a valuable asset for service providers, as failures often emerge post-deployment and demand specialized expertise and resources to resolve them. In this work, we introduce SURE, the first end-to-end framework that SecUrely REpairs failures flagged by users of diffusionbased services. SURE enables the service provider to securely collaborate with an external third-party specialized in model repairing (i.e., Model Repair Institute) without compromising the confidentiality of user feedback, the service provider's proprietary model, or the Model Repair Institute's proprietary repairing knowledge. To achieve the best possible efficiency, we propose a co-design of a model editing algorithm with a customized two-party cryptographic protocol. Our experiments show that SURE is highly practical: SURE securely and effectively repairs all 32 layers of Stable Diffusion v1.4 in under 17 seconds (four orders of magnitude more efficient than a general baseline). Our results demonstrate that practical, secure model repair is attainable for large-scale, modern diffusion services.

Despite the general capabilities of Large Language Models (LLMs) like GPT-4, these models still request fine-tuning or adaptation with customized data when meeting the specific business demands and intricacies of tailored use cases. However, this process inevitably introduces new safety threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) under the setting of Language-Model-as-a-Service (LMaaS), where the model's safety has been significantly compromised by fine-tuning on users' uploaded examples that contain just a few harmful examples. Though potential defenses have been proposed that the service providers of LMaaS can integrate safety examples into the fine-tuning dataset to reduce safety issues, such approaches require incorporating a substantial amount of data, making it inefficient. To effectively defend against the FJAttack with limited safety examples under LMaaS, we propose the Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. In particular, service providers will construct prefixed safety examples with a secret prompt, acting as a backdoor trigger. By integrating prefixed safety examples into the fine-tuning dataset, the subsequent fine-tuning process effectively acts as the backdoor attack, establishing a strong correlation between the secret prompt and safety generations. Consequently, safe responses are ensured once service providers prepend this secret prompt ahead of any user input during inference. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 prefixed safety examples, the maliciously fine-tuned LLMs will achieve similar safety performance as the original aligned models without harming the benign performance. Furthermore, we also present the effectiveness of our method in a more practical setting where the fine-tuning data consists of both FJAttack examples and the fine-tuning task data.

The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of web-collected data, which may inadvertently include sensitive personal data.

Cloud-based machine learning inference is an emerging paradigm where users query by sending their data through a service provider who runs an ML model on that data and returns back the answer. Due to increased concerns over data privacy, recent works have proposed Collaborative Inference (CI) to learn a privacy-preserving encoding of sensitive user data before it is shared with an untrusted service provider. Existing works so far evaluate the privacy of these encodings through empirical reconstruction attacks. In this work, we develop a new framework that provides formal privacy guarantees for an arbitrarily trained neural network by linking its local Lipschitz constant with its local sensitivity. To guarantee privacy using local sensitivity, we extend the Propose-Test-Release (PTR) framework to make it tractable for neural network queries. We verify the efficacy of our framework experimentally on real-world datasets and elucidate the role of Adversarial Representation Learning (ARL) in improving the privacy-utility trade-off.

Abstract--Federated learning (FL) offers privacy preserving, distributed machine learning, allowing clients to contribute to a global model without revealing their local data. As models increasingly serve as monetizable digital assets, the ability to prove participation in their training becomes essential for establishing ownership. In this paper, we address this emerging need by introducing FedPoP, a novel FL framework that allows non-linkable proof of participation while preserving client anonymity and privacy without requiring either extensive computations or a public ledger . FedPoP is designed to seamlessly integrate with existing secure aggregation protocols to ensure compatibility with real-world FL deployments. We provide a proof of concept implementation and an empirical evaluation under realistic client dropouts. In our prototype, FedPoP introduces 0.97 seconds of per-round overhead atop securely aggregated FL and enables a client to prove its participation/contribution to a model held by a third party in 0.0612 seconds. These results indicate FedPoP is practical for real-world deployments that require auditable participation without sacrificing privacy. Federated learning (FL) [1] has become one of the innovative distributed machine learning structures wherein private data holders (a.k.a. The most common FL setting involves three parties: a server who initiates a model and aggregates training data (local models) from clients, a large number of clients who collaboratively train the model, and a service provider who deploys the model to provide services to its users. In a nutshell, an FL system consists of iterative aggregation rounds where 1) the server sends global model parameters to clients; 2) each client trains the model using its own private data and transmits updated parameters to the server; and 3) the server aggregates the updated parameters sent by the clients into a new global model using an aggregation procedure (e.g., FedAvg [1], FedQV [2]). The final global model is delivered to the service provider when the training is completed.

The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of web-collected data, which may inadvertently include sensitive personal data.

In the current paradigm of digital personalized services, the centralized management of personal data raises significant privacy concerns, security vulnerabilities, and diminished individual autonomy over sensitive information. Despite their efficiency, traditional centralized architectures frequently fail to satisfy rigorous privacy requirements and expose users to data breaches and unauthorized access risks. This pressing challenge calls for a fundamental paradigm shift in methodologies for collecting, storing, and utilizing personal data across diverse sectors, including education, healthcare, and finance. This paper introduces a novel decentralized, privacy-preserving architecture that handles heterogeneous personal information, ranging from educational credentials to health records and financial data. Unlike traditional models, our system grants users complete data ownership and control, allowing them to selectively share information without compromising privacy. The architecture's foundation comprises advanced privacy-enhancing technologies, including secure enclaves and federated learning, enabling secure computation, verification, and data sharing. The system supports diverse functionalities, including local computation, model training, and privacy-preserving data sharing, while ensuring data credibility and robust user privacy.

We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking third-party service-distribution platforms to prepend adversarial prompts, and (2) publishing back-doored open-source checkpoints fine-tuned with attacker data. Unlike conventional attacks that degrade accuracy, AEA subvert information integrity, causing models to return covert ads, propaganda, or hate speech while appearing normal. We detail the attack pipeline, map five stakeholder victim groups, and present an initial prompt-based self-inspection defense that mitigates these injections without additional model retraining. Our findings reveal an urgent, under-addressed gap in LLM security and call for coordinated detection, auditing, and policy responses from the AI-safety community.