ddosi
Featured
PacketLens
PacketLens is a pure front-end, offline pcap analysis tool that runs entirely in the browser, supporting deep protocol decoding, HTTPS decryption, and million-packet instant loading without any backend.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It provides the clearest structured taxonomy of the verifiable/private AI landscape, combining a 2x2 framework with detailed per-approach and per-paper references, plus a curated org-level landscape of who builds what.
Who it is for
- Cryptography researchers and engineers
- ML practitioners seeking verifiable or private inference
- Decentralized AI project teams
- Auditors and security professionals assessing AI trustworthiness
Use cases
- Selecting the right cryptographic approach (e.g., ZK, MPC, FHE) for a given AI phase
- Understanding trade-offs between verifiability and privacy in AI systems
- Identifying key companies and research groups working on each technique
- Gaining a comprehensive overview of open problems and cost structures in trustable AI
Strengths
- Comprehensive 2x2 taxonomy covering inference/training and verifiability/privacy
- Links to a generated site with one page per approach and per paper, including data provenance
- Includes a landscape map of companies and research teams, distinguishing genuinely focused zkML startups from adjacent projects
- Discusses cost trade-offs (e.g., ~1000x compute overhead for verifiability) and trust models
Considerations
- Not a tool or library; it's a curated knowledge base and reference
- The landscape may become outdated as the field evolves quickly
- Focuses mainly on cryptographic techniques; non-cryptographic approaches (e.g., incentives, TEEs) are labeled adjacent and not deeply covered
README quick start
zkAI: Verifiable and Private AI
A systematization of knowledge on making AI trustworthy, from zkSecurity. The "zk" is historical: zero-knowledge proofs are one technique here, not the scope.
The full SoK is a generated site, one page per approach and one per paper, with every number rendered from the data and carrying its provenance.
The map
The field is a 2×2: what phase of the model's life you protect, and what property you want. Each cell is served by several cryptographic (and non-cryptographic) approaches.
| Verifiability (prove it was done right) | Privacy (hide the data/model during compute) | |
|---|---|---|
| Inference | Proving inference: zkML. DeepProve, Jolt Atlas, zkPyTorch, zkGPT, zkLLM. | Private inference: 2PC/MPC/FHE. Iron, BOLT, CipherGPT, Nimbus. |
| Training | Proving training: zkPoT. Kaizen, zkDL, Optimum Vicinity, ZKBoost. | Private training: MPC/HE. PriFT, and verifiable-FL hybrids. |
The technique is not the axis. A cell can be filled by ZK proofs, MPC, FHE, trusted hardware (TEEs), optimistic fraud proofs, or trace sampling, at very different cost/trust trade-offs. Verifiability buys correctness (a third party can trust the result) at ~1000× compute. Privacy buys confidentiality from a counterparty (usually only a semi-honest one) at the price of heavy communication or homomorphic compute. They are different guarantees, and most systems give one, not both.
Within the verifiability column, the ZKP-VML survey splits what is being proven three ways, and we add a fourth.
Description
using agents to monitor proving training and inference techniques
Related repositories
Similar projects matched by category, topics, and programming language.
ViffyGwaanl
Featured
kimi-k3-learn
An interactive learning system that turns the 47-page Kimi K3 technical report into a single offline HTML file with running algorithms, 3D visualizations, spaced repetition quizzes, and a smart highlighting QA tool.
iamtechartist
Featured
human-cell-visualizer
An interactive 3D visualization of three human cell types using Three.js, WebGL particles, and custom GLSL shaders, allowing users to rotate, zoom, morph, and explore annotated structures.