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.

Research · 101Technical Guide · 2Advisory Analysis · 5Guide · 1News · 3

Latest Posts

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
Deserialization Threats

Joblib Model Suspicious Code Execution Detected at Model Load Time

Identifies suspicious execution sequences during a Joblib model load indicating potentially obstructed deserialization threats.

2026-04-27Read
Deserialization Threats

Joblib / Scikit-Learn Arbitrary Code Execution (ACE)

Identifies insecure object deserialization attacks utilizing the popular Scikit-Learn Joblib persistency library, granting attackers remote execution...

2026-04-27Read
Deserialization Threats

GGUF Metadata Parsing Flaws (Llama.cpp Buffer Overflows)

Identifies highly critical buffer overflow attacks manipulating the internal metadata and vocabulary tensors of GGUF files to exploit C++ parsers like...

2026-04-27Read
Deserialization Threats

Extraction-Triggered Environment Override (Path Overwriting)

An advanced attack where a malicious model archive weaponizes extraction processes to overwrite critical environment-level objects, seizing control of...

2026-04-27Read
Deserialization Threats

Execution of Arbitrary Code via Model Config Architecture Targets

Identifying advanced threats where malicious executables are obfuscated as configuration objects inside an ML model archive, triggering Remote Code...

2026-04-27Read
Deserialization Threats

Machine Learning Archive Zip Slip (Path Traversal) Threat

Identifies severe path traversal vulnerabilities (Zip Slip) occurring during the automated extraction of compressed machine learning model packages.

2026-04-27Read