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 Not All Synthetic Data Is Yours to Learn From (2026) Probing Privacy Leaks in LLM-based Code Generation via Test Generation (2026…
…Detecting Privacy Leakage Risks in MCP Servers (2026) Please give a thumbs up to this comment if you found it helpful! If you want recommendations for any Paper on Hugging Face checkout…
…The following papers were recommended by the Semantic Scholar API Do Phone-Use Agents Respect Your Privacy? (2026) KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation (2026) OpenComputer: Verifiable Software…
…The work is especially relevant for on-device AI, privacy-sensitive applications, edge deployment, and production RAG systems with limited compute budgets. Accepted to ECML PKDD 2026 Applied Data Science Track. Author…
…Revisiting Issue-Commit Linking with LLM-Assisted Retrieval (2026) Probing Privacy Leaks in LLM-based Code Generation via Test Generation (2026) REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped…
…A Multimodal Foundation Model for Adversarial Content and AI Safety (2026) Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection (2026) Are Text-to-Image Models Inductivist Turkeys? A…
…everything up to "Submit the job to Hugging Face Jobs"? So cool! Is there data privacy when doing this? Is it posted privately to a personal/team hub? Could this be done…
…whether an action is acceptable depends on local privacy norms, organizational policies, and user expectations that resist pre-deployment specification. This creates a practical gap: guardrails must adapt to their own operating…
…Every major open trajectory dataset for CLI coding agents is collected primarily under the same scaffold, OpenHands, but practitioners pick their scaffold on cost, licensing, latency and data privacy. We measured what…
…Sparse Feature Analysis (2026) Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations (2026) Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language…