相关论文: It Takes Two: Complementary Self-Distillation for …

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel…

Face identity provides a powerful signal for deepfake detection. Prior studies show that even when not explicitly modeled, classifiers often learn identity features implicitly. This has led to conflicting views: some suppress identity cues…

Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context to identify and mitigate potential risks. Though researchers…

Differential privacy (DP) has become the gold standard for privacy-preserving data analysis, but its applicability can be limited in scenarios involving complex dependencies between sensitive information and datasets. To address this, we…

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

The multicontextual nature of immersive VR makes it difficult to ensure contextual integrity of VR-generated information flows using existing privacy design and policy mechanisms. In this position paper, we call on the HCI community to do…

In this paper, we argue that mutual distillation between reinforcement learning policies serves as an implicit regularization, preventing them from overfitting to irrelevant features. We highlight two separate contributions: (i)…

Federated learning (FL) is a widely adopted privacy-preserving distributed learning framework, yet its generalization performance remains less explored compared to centralized learning. In FL, the generalization error consists of two…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

Self-Sovereign Identity (SSI) is an identity model centered on the user. The user maintains and controls their data in this model. When a service provider requests data from the user, the user sends it directly to the service provider,…

Identifying contextual integrity (CI) and governing knowledge commons (GKC) parameters in privacy policy texts can facilitate normative privacy analysis. However, GKC-CI annotation has heretofore required manual or crowdsourced effort. This…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

Collaborative inference in next-generation networks can enhance Artificial Intelligence (AI) applications, including autonomous driving, personal identification, and activity classification. This method involves a three-stage process: a)…

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data. Model heterogeneity and catastrophic forgetting are two crucial…

The proliferation of LLM-based agents has led to increasing deployment of inter-agent collaboration for tasks like scheduling, negotiation, resource allocation etc. In such systems, privacy is critical, as agents often access proprietary…

CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model…