#privacy-risk News & Analysis

4 articles tagged with #privacy-risk. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBearisharXiv – CS AI · Jun 57/10

🧠

When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents

Researchers introduced RBI-Eval, a measurement framework revealing that language model agents inconsistently handle sensitive memory content in conversations. The study found that models like Claude and DeepSeek integrate sensitive information 51-83% more readily when memory is available compared to baseline, suggesting critical safety gaps in memory-augmented AI systems.

🧠 GPT-5🧠 Claude

AIBearisharXiv – CS AI · Apr 157/10

🧠

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems

Researchers have identified a critical privacy vulnerability in LLM-based multi-agent systems, demonstrating that communication topologies can be reverse-engineered through black-box attacks. The Communication Inference Attack (CIA) achieves up to 99% accuracy in inferring how agents communicate, exposing significant intellectual property and security risks in AI systems.

AIBearisharXiv – CS AI · Apr 147/10

🧠

What do your logits know? (The answer may surprise you!)

Researchers demonstrate that AI model logits and other accessible model outputs leak significant task-irrelevant information from vision-language models, creating potential security risks through unintentional or malicious information exposure despite apparent safeguards.

AINeutralarXiv – CS AI · Jun 56/10

🧠

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

Researchers introduce PropMe, a framework that distinguishes between LLMs' capability to leak training data when directly attacked versus their propensity to do so during normal use. Testing on open models reveals a significant gap: while models can be forced to reproduce training data through adversarial prompts, they rarely do so voluntarily, suggesting memorization risk is lower in practical deployment than worst-case evaluations suggest.