Spectre attack against SGX enclave

[NeurIPS'23] Speculative Decoding with Big Little Decoder

Microarchitectural exploitation and other hardware attacks.

🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.

KLEESpectre is a symbolic execution engine with speculation semantic and cache modelling

Variant 1 of the Spectre attack which is to bypass the bounds checks in the target process and retrieve the private data. Here in this example, I have demonstrated how to retrieve a string data using the attack.

Package speculatively provides a simple mechanism to re-execute a task in parallel only after some initial timeout has elapsed.

Experimental implementation of speculative model serving

Spectre attack variant 1 is used here to extract an image data buffer from a program. The output image data is then decoded and median filters are applied to remove the hot pixels in the output image. Here I have included files for RGB and base64 format.

Research project about Spectre attack on XiangShan open-source RISC-V processor

Run AI models too large for your Mac's memory — at near-full speed. Intelligent expert caching, speculative execution, and 15+ research techniques for MoE inference on Apple Silicon.

Proof of concept code for the Spectre CPU exploit.

Phantom Metal Taste — speculative execution side-channel research

Extension of the ScheduleFlow Simulator to allow speculative request times at submission and during backfill

Run large MLX models on Apple Silicon with flash weight streaming, using native precision beyond RAM limits

A lock-free state transition engine utilizing optimistic concurrency control (Block-STM) for high-throughput parallel execution. (CMU 15-418)