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.
Latest Posts
Python Pickle Arbitrary Code Execution Detected
Discover how Python's built-in Pickle serialization module enables severe Arbitrary Code Execution (ACE) vulnerabilities within machine learning...
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...
LlamaFile Binary Shell Overloading Threat
Identifies highly specific payload injections targeting LlamaFile's native Cosmopolitan Libc architecture—hijacking the dual-executable parsing...
LiteRT Delegation Core Execution Exploits
Represents critical systemic integration failures explicitly targeting localized Hardware Delegation Frameworks (Core ML / NNAPI / Hexagon), exploiting...
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...
ONNX Model Contains Embedded File Threats
AI Models can distribute additional malicious binaries hidden inside model file payloads. Eresus Sentinel detects these backdoor packages masked within...
Keras Model Custom Layer Detected at Model Run Time
Highlights specific Keras deployments dynamically compiling complex custom layers entirely operating outside strict deserialization bounds. Poses...
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...
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...