Tracked topic
Protect your digital life with the latest privacy news, covering smart device surveillance risks and OS security backdoors.
Cloud agents typically send user messages to remote LLMs and store conversation traces in memory systems (e.g., Mem0, LangMem, Memobase) for long-term personalization. This creates a large privacy attack surface: plaintext prompts and logs may contain PII, medical/financial data, credentials cloud memory stores can leak via retrieval, prompt injection, inversion, or misconfiguration naïve mitigation (e.g., *** masking) destroys task semantics, harming retrieval and personalization Goal: reduce privacy leakage without sacrificing utility.
Paper page - MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents… The following papers were recommended by the Semantic Scholar API Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication 2026 PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning 2026 DDP-SA: Scalable P… …
… Model Name Parameters Method HuggingFace Link 🤗 MemPrivacy-4B-RL 4B RL IAAR-Shanghai/MemPrivacy-4B-RL 🤗 MemPrivacy-4B-SFT 4B SFT IAAR-Shanghai/MemPrivacy-4B-SFT 🤗 MemPrivacy-1.7B-RL 1.7B RL IAAR-Shanghai/MemPrivacy-1.7B-RL 🤗 MemPrivacy-1.7B-SFT 1.7B SFT IAAR-Shanghai/MemPrivacy-1.7B-SFT Evaluation … …
… On three agentic benchmarks under strict privacy settings, PAAC dominates the Pareto frontier of privacy and accuracy, improving average accuracy by 15-36\% and reducing average leakage by 2-6times over state-of-the-art device-cloud baselines, with the largest margins on privacy targets outside fix… …