Amplifying Latency and Cost of LLM Inference Via Rowhammer Attack

Large language models LLMs achieve high inference efficiency using optimized GPU kernels generated by just-in-time JIT compilation frameworks such as Triton. Triton compiles GPU kernels through an MLIR/LLVM-based pipeline. We investigate whether a Rowhammer-induced bit-flip in the CPU's DRAM can...

CVE-2026-73081

Activepieces is an open source AI workflow automation platform. Prior to 0.80.0, the worker's code-compilation pipeline builds the on-disk path for a Code step from the step's name and passes that path to a shell-invoked build command. A step name containing shell metacharacters can break out of...