Tooling

A batch of NDSS papers covering URL shortening service abuse, GPU driver fuzzing, ZK compiler testing, and latency improvements for DAG-based consensus.

Hardware side channels through power telemetry, nested enclaves in CVMs, contextual vulnerability scoring, agentic repair, and fuzzing tool boundaries.

New papers on Common Criteria evaluation failures, LLM coding agent skills, and MoE router telemetry privacy.

A review of Google Jules’s agent architecture, capabilities, and vulnerabilities to prompt injection based on public security research and unofficial internals documentation.

An exhaustive architectural exploration of System 2 AI, process reward modeling, inference-time compute scaling, and the evolution of verifiable reasoning in large language models.