EresusSecurity
Research & Intelligence

Eresus research, advisory, and security news

We collect writing, advisories, and current-event analysis around AI security, the MCP ecosystem, application security, and real attack chaining here.

Guide · 27News · 4Case Study · 3Research · 84Technical Guide · 2Advisory Analysis · 5Advisory · 2

Latest Posts

Executable Config Threats

ONNX Unsafe Attribute Parsing (Arbitrary Code Execution / DoS)

A severe vulnerability detecting weaponized ONNX models exploiting legacy internal processing loops—manipulating attributes and external data extraction...

2026-04-27Read
Runtime Threats

LlamaFile Binary Shell Overloading Threat

Identifies highly specific payload injections targeting LlamaFile's native Cosmopolitan Libc architecture—hijacking the dual-executable parsing...

2026-04-27Read
Runtime Threats

LiteRT Delegation Core Execution Exploits

Represents critical systemic integration failures explicitly targeting localized Hardware Delegation Frameworks (Core ML / NNAPI / Hexagon), exploiting...

2026-04-27Read
Runtime Threats

LiteRT Out-of-bounds Read/Write (Heap Corruption)

A severe vulnerability exploiting malformed shape descriptors inside customized operators executing natively on edge GPUs—triggering out-of-bounds...

2026-04-27Read
Backdoor Threats

PAIT-ONNX-200: Embedded Malicious Binary Artifacts and Polyglots in ONNX Models

Analysis of supply chain trojans within ONNX model files, exploring how adversaries embed hidden executables and polyglot payloads inside neural network protobuf structures.

2026-04-10Read
Runtime Threats

PAIT-KERAS-301: Deferred Code Execution via Malicious Custom Layers in Keras Models

Analysis of runtime exploitation in Keras and HDF5 models, detailing how adversaries conceal unauthorized Python execution inside custom Layer definitions that trigger only during inference.

2026-04-10Read
Deserialization Threats

Keras Model Lambda Layer Suspicious Operator Detected at Model Load Time

High-severity deserialization threat identifying suspicious or highly uncharacteristic operational routines within a Keras Lambda layer payload upon...

2026-04-27Read
Deserialization Threats

Keras Extracted Object Hijacking & DoS Corruptions

Advanced exploitation where seemingly secure Keras architectures (.h5 or .keras) manipulate intrinsic layer attributes or geometry to crash execution...

2026-04-27Read
Deserialization Threats

Keras HDF5 Lambda Layer Arbitrary Code Execution

Identifies insecure legacy Keras objects (`.h5` or `.hdf5`) attempting to deserialize and execute malicious Python scripts hidden inside Lambda layer...

2026-04-27Read