- Model attacks
- Privacy & data
Reliable Estimation of Differential Privacy under Selection Bias
arXiv:2610.27021v1 Announce Type: new Abstract: Statistical privacy audits are essential for verifying the theoretical…
No signal on this page matches that topic.
arXiv:2610.27021v1 Announce Type: new Abstract: Statistical privacy audits are essential for verifying the theoretical…
arXiv:2610.27026v1 Announce Type: new Abstract: Traffic cameras support useful analysis, but their outputs can reveal…
arXiv:2610.27135v1 Announce Type: new Abstract: With the advancement of powerful AI chips, on-device machine learning…
arXiv:2610.27152v1 Announce Type: new Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to…
arXiv:2610.27213v1 Announce Type: new Abstract: Personalized large language models (LLMs) increasingly rely on…
arXiv:2610.27244v1 Announce Type: new Abstract: Agent systems are shifting from task-scoped tool-use agents to…
arXiv:2610.27249v1 Announce Type: new Abstract: Graph pebbling is the model in which the memory cost of memory-hard…
arXiv:2610.27259v1 Announce Type: new Abstract: The rapid evolution of Large Language Models is fueled by massive…
arXiv:2610.27383v1 Announce Type: new Abstract: Finding vulnerabilities early, before they can affect the production system, is important for reducing the risk of any software attacks. However…
arXiv:2610.27470v1 Announce Type: new Abstract: Federated learning (FL) is a distributed machine learning paradigm that…
arXiv:2610.27473v1 Announce Type: new Abstract: Text-to-image models can generate visual concepts that their prompts…
arXiv:2610.27533v1 Announce Type: new Abstract: Machine learning benchmarks act as guideposts for model development and…
Google released TorchTPU as open source, giving PyTorch developers a native way to run models on the company’s Tensor…
The JFrog Security Research team identified malicious code in `litellm` 1.107.0, a widely used Python interface and proxy for large language model providers. The payload wheels are a functional copy…
A Toronto man says he was shocked and devastated when a BMW dealership revoked an offer to buy back his car, telling…
A BMW dealer blamed an AI chatbot for a $7,000 pricing mistake. The customer says he never knew he was negotiating with…
A Canadian BMW owner recently thought he had negotiated a great deal to sell his car back to a local dealer. After a…
AIID editor's note: This judgment has been abridged to fit AIID's 50,000-character limit. Paragraphs 54-118 and…
Artificial intelligence ("AI") is rapidly reshaping legal practice. Lawyers are increasingly using AI tools for drafting, research assistance, document review, summarisation and litigation…
CERT-In Advisory CIAD-2026-0049 AI Agents as Attack Vectors: Unauthorized Access by Agents under Evaluation and Misuse…