Mihai Maruseac
where else to find them
linkedin:mihai-maruseac
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 11 in the filters
on a stage with
- Noah Elzner2×
- Hasan Yasaronce
- Kate Stewartonce
all 5 in the filters
who talks about the same things
- Parth Patel7 talks
- Michael Lieberman36 talks
- Jay White9 talks
- Sarah Evans10 talks
- Dan Lorenc21 talks
- Olimpiu Pop8 talks
| title | conference | date |
|---|---|---|
| Taming ML’s Wild West: Practical Model Signing with Sigstore on Kaggle | AI By the Bay 2025 | 2025-11-17 |
Practical steps for attesting model integrity: use the Python library model-signing (pip install model-signing) with Sigstore to create short‑lived OIDC-backed… | ||
| From Model To Trust: Building Upon Tamper-proof ML Metadata Records | PyTorch Conference 2025 | 2025-10-22 |
Demonstrates a working system that cryptographically signs bundles of ML artifacts (models, datasets, model cards) using OpenSSF Model Signing, produces… | ||
| Strengthening Software Supply Chains: Harmonizing SLSA Provenance and SPDX SBOM for Better Adoption | Open Source Summit North America 2025 | 2025-06-23 |
SLSA provenance ties each build to its workflow while SPDX SBOM lists every component; together they pinpoint what went into an artifact, who built it, and how… | ||
| Taming the Wild West of ML: Practical Model Signing with Sigstore on Kaggle | DevConf.CZ 2025 | 2025-06-12 |
Train a simple TensorFlow/Keras digit model, upload to a hub, show an attacker tampering with a saved checkpoint and causing a malicious or crashing model… | ||
| End-to-End Secure ML Development | SOSS Fusion 2024 | 2024-10-22 |
Covers an end-to-end recipe that actually signs and verifies models using model signing with six store and logs inclusion proofs so model hubs can verify… | ||
| We Know Security but How Do We Secure GenAI End-to-End? | SOSS Community Day Europe 2024 | 2024-09-19 |
Claims concrete fixes: sign models at train time, hash formats the same way used for signatures, and generate salsa provenance for each training cycle (data… | ||
| ML Model Signing: Cryptographically Paving the Way to Provenance in Machine Learning Models | SOSS Community Day Europe 2024 | 2024-09-19 |
An open source library creates a signed manifest of every file or hash shards inside an ML model, converts that manifest to an in-toto payload and records the… | ||
| End-to-end secure ML Development | Carolina Code Conference 2024 | 2024-08-23 |
Demonstrates concrete defenses: Sigstore short-lived signatures for gigabyte‑scale models, a model‑signing library that hashes checkpoints deterministically… | ||
| Model transparency for AI/ML security | Scale By the Bay 2023 | 2023-11-13 |
Claims that model supply chain compromise rises alongside a >700% YoY jump in supply‑chain attacks and that real malicious LLMs already exist, and demonstrates… | ||
| Bazel Rules | BazelCon 2023 | 2023-10-24 |
Project converts 250,000 lines of native Java (380k with tests) into Starlark where current rule code is ~10,000 lines of Starlark, moving outer rule defs… | ||
| Secure your Bazel artifacts using SLSA | BazelCon 2023 | 2023-10-24 |
With a 700+% YoY increase in supply chain attacks the project automates SLSA provenance for Bazel builds via a GitHub Actions reusable workflow that runs… | ||
| Where Is the GUAC? | SupplyChainSecurityCon @ OSS NA 2023 | 2023-05-10 |
GUAC ingests SBOMs and attestations (SPDX, CycloneDX, SALSA) from local folders or OCI into a knowledge graph and exposes it via GraphQL query layer and… | ||
| It's Dangerous To SLSA Alone Out There! Take This Artifact Knowledge Graph! | KubeCon + CloudNativeCon North America 2022 | 2022-10-24 |
A knowledge graph called guac ingests SBOMs, in-toto/SLSA attestations, Sigstore records and VEX feeds, correlates them in Neo4j and answers blast‑radius… | ||
| nothing matches | ||