Home Knowledge Base Adaptive Privacy Control

Adaptive Privacy Control

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs

Announce Type: new Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitive information; while on the downstream task side, model reasoning depends on rich visual context that may itself be privacy-sensitive.

arXiv CS 2d ago

Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries

Announce Type: new Abstract: Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state, and per-device updates-cannot be exported outside an administrative boundary. Existing distributed and federated stacks typically assume cross-site model exchange and then retrofit privacy mechanisms, which complicates compliance and makes auditing brittle. We present Echelon, a...

arXiv CS 7d ago

Private and Stable Test-Time Adaptation with Differential Privacy

Announce Type: new Abstract: Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs.

arXiv CS 8d ago

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Announce Type: replace Abstract: Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to the user.

arXiv CS 9d ago

LifeSide: Benchmarking Agents as Lifelong Digital Companions

Announce Type: new Abstract: Lifelong digital companions must integrate cross-session cues, continually update their understanding of users, and adapt to shifting privacy boundaries. Existing evaluations fail to capture this, testing memory recall and short-term empathy in isolation. To bridge this gap, we introduce \benchmark, a benchmark centered on multi-session \textit{Memory-Emotion-Environment} loops.

arXiv CS 6d ago

KDE at 30

KDE at 30 KDE is turning 30 this year! Three decades of passionate community effort against all odds; delivering control, privacy, and freedom to our users; and tons and tons of software. We will be updating this page frequently with new content, exciting 30th Anniversary news, things you can participate in, updated merch you can get, and much more!

Hacker News 9d ago

A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models

arXiv:2605.31080v1 Announce Type: new Abstract: Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy and intellectual-property constraints may favour small on-premise vision-language models (VLMs). This pilot study investigates curator-guided multilingual art description with Qwen2.5-VL-3B-Instruct for German, Romanian, and Serbian. We construct a parallel BLV-oriented caption corpus from...

arXiv CS 9d ago

A walking tour of surveillance infrastructure in Seattle

Note: this guide is a work in progress and may change at any time! We’ve done our best to cite our sources, but this page has not been professionally fact-checked. This workshop was first run as part of two pilot workshops with the Tech Equity Coalition, in partnership with the ACLU of Washington, in October 2019.

Hacker News 8d ago

Is predictive text giving you mistakes and 'hallucinations'? You're not alone

Predictive text in 'demonstrable decline' with introduction of AI-based language models Thu 11 Jun 2026 at 6:21am The next "butks" stop. Eating a "banns bc a". It's "mi longer shiny sync".

ABC Australia 1h ago

Quantum-Inspired Reinforcement Learning for Low-Latency Intrusion Detection in V2X and Internet-of-Vehicles Networks

Announce Type: new Abstract: Smart cities increasingly depend on dense edge, IoT, and vehicular networks to deliver critical urban services, including traffic control, connected mobility, infrastructure monitoring, and energy management. In this ecosystem, the Internet of Vehicles (IoV) is central to intelligent transportation, enabling continuous communication among vehicles, roadside infrastructure, and cloud-edge platforms. This connectivity, however, also enlarges the attack surface and...

arXiv CS 1d ago