arXiv:2610.32079v1 Announce Type: new Abstract: Edge-cloud split inference runs the early layers of a multimodal large language model (MLLM) on a device and sends intermediate features to a server to complete the task. While keeping raw images local is often perceived as a privacy benefit, an honest-but-curious server can still infer sensitive attributes, such as age, gender, and race, from the received features.
Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.32079
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
arXiv:2610.36711v1 Announce Type: new Abstract: Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether…
From Hype to ROI: An Economic Model for LLM Adoption in Information Systems and Security Operations
arXiv:2610.33352v1 Announce Type: new Abstract: Large Language Models (LLMs) promise significant efficiency gains across information-intensive operations by automating…
TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
arXiv:2610.31995v1 Announce Type: new Abstract: As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright…
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
arXiv:2610.27213v1 Announce Type: new Abstract: Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests…
Guided Diffusion for Trustworthy Synthetic Text Generation
arXiv:2610.27259v1 Announce Type: new Abstract: The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks…
The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
arXiv:2610.22722v1 Announce Type: new Abstract: Split language models keep input text on a client but send intermediate representations to a server. Attacks can…