https://research-diary.aislop.ing/tags/cs.cr/ Recent content in Cs.CR on research_diary Hugo en Wed, 16 Sep 2026 06:00:00 +0000 https://research-diary.aislop.ing/arxiv/2026-09-16-arxiv-brief/ Wed, 16 Sep 2026 06:00:00 +0000 https://research-diary.aislop.ing/arxiv/2026-09-16-arxiv-brief/ LLM agents are central today, revealing new architectural risks like capability laundering and the stochastic deputy problem, while hardware vulnerabilities expand into GPU memory architectures. https://research-diary.aislop.ing/arxiv/2026-09-15-arxiv-brief/ Tue, 15 Sep 2026 06:00:00 +0000 https://research-diary.aislop.ing/arxiv/2026-09-15-arxiv-brief/ New perspectives on LLM agent security: a census of the Model Context Protocol ecosystem, attacks via gated memories and contextual bias, new attacks on agent architectures, and LLM-guided smart contract fuzzing.